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

    Neuronpedia

    Jacobian LensNEW
    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. 43861
    Prev
    Next
    INDEX
    Explanations

    assistant

    np_max-act · gemini-2.0-flash

    assistant self-identification and boilerplate introduction lines describing a helpful AI assistant persona.

    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
     Kay
    -0.08
    “I
    -0.07
     전
    -0.07
     debilitating
    -0.07
    \"\
    -0.06
     בחינם
    -0.06
    べ
    -0.06
    Hu
    -0.06
     Soy
    -0.06
     policeman
    -0.06
    POSITIVE LOGITS
    ящ
    0.07
    GES
    0.07
    行為
    0.07
    ibilidad
    0.07
    irty
    0.07
    把它
    0.07
    decay
    0.07
    ⵔ
    0.07
    .extensions
    0.07
    blocking
    0.06
    Activations Density 0.025%

    No Known Activations