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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    6. 22701
    Prev
    Next
    INDEX
    Explanations

    Manhattan Project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scroll
    -0.09
    租金
    -0.07
    _ELEMENT
    -0.07
    ≠
    -0.07
    딸
    -0.07
    Immutable
    -0.07
    Password
    -0.07
    Nano
    -0.06
    (Entity
    -0.06
    .inventory
    -0.06
    POSITIVE LOGITS
     erfolgre
    0.07
     바랍니다
    0.07
     לימודי
    0.07
    .flowLayoutPanel
    0.07
    (prom
    0.07
    usp
    0.07
    ↵↵    ↵
    0.07
     Yıl
    0.07
    𝘄
    0.06
    <string
    0.06
    Activations Density 0.012%

    No Known Activations