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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 27326
    Prev
    Next
    INDEX
    Explanations

    #ifndef

    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
     giảng
    -0.08
    אישור
    -0.08
    ħ
    -0.07
    犏
    -0.07
    .ind
    -0.07
    .getID
    -0.07
    虬
    -0.07
     dash
    -0.07
    aycast
    -0.07
     woodland
    -0.07
    POSITIVE LOGITS
    ation
    0.07
    ALER
    0.07
     often
    0.07
    _su
    0.07
     own
    0.06
    _Call
    0.06
    .isNullOrEmpty
    0.06
    loat
    0.06
    要看
    0.06
    (category
    0.06
    Activations Density 0.008%

    No Known Activations