© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 116146
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    assistant-style turn openings and polite meta-discourse that acknowledges, agrees with, or validates the other speaker’s points.

    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
    =node
    -0.08
    Insurance
    -0.07
    itable
    -0.07
    [position
    -0.07
     grande
    -0.07
    drawing
    -0.07
    obra
    -0.07
     Panda
    -0.06
     paranoia
    -0.06
     stealth
    -0.06
    POSITIVE LOGITS
    响
    0.07
    柱
    0.07
    延迟
    0.07
    QUIRED
    0.07
    没能
    0.07
    xed
    0.07
    \application
    0.06
     XIII
    0.06
    問
    0.06
    .executeQuery
    0.06
    Activations Density 0.264%

    No Known Activations