© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 128253
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    assistant-role replies that open with first‑person apologies and statements of not understanding or lacking information, often requesting clarification.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Generally
    -0.07
    /loader
    -0.07
    _scr
    -0.07
    )↵
    -0.07
    oleans
    -0.07
    (round
    -0.07
     ```
    -0.06
    `).
    -0.06
    .Ge
    -0.06
    列车
    -0.06
    POSITIVE LOGITS
    מקד
    0.07
     reactor
    0.07
    BJECT
    0.07
     пара
    0.07
    Tracker
    0.07
    嘁
    0.06
    _contacts
    0.06
    웢
    0.06
    ution
    0.06
    domains
    0.06
    Activations Density 0.067%

    No Known Activations