Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10869
    Prev
    Next
    INDEX
    Explanations

    legal appeal

    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_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
     Maths
    -0.07
     rave
    -0.07
     seks
    -0.07
     flyer
    -0.07
     אליה
    -0.07
    بار
    -0.07
    _non
    -0.07
     Care
    -0.06
     r
    -0.06
     fearing
    -0.06
    POSITIVE LOGITS
    锥
    0.07
    🥨
    0.07
    licit
    0.07
    cken
    0.07
    uth
    0.06
    DataFrame
    0.06
    ated
    0.06
    ドル
    0.06
    ume
    0.06
    >").
    0.06
    Activations Density 0.013%

    No Known Activations