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. 16477
    Prev
    Next
    INDEX
    Explanations

    {

    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
    桑
    -0.07
     görüş
    -0.07
     spanish
    -0.07
    (Color
    -0.06
    توفر
    -0.06
    .full
    -0.06
    notEmpty
    -0.06
    感じ
    -0.06
    clazz
    -0.06
    .setting
    -0.06
    POSITIVE LOGITS
     inertia
    0.07
    חובה
    0.07
     مق
    0.07
    であ
    0.07
    ←
    0.07
     Activation
    0.07
     Conv
    0.07
     devices
    0.07
    xae
    0.07
     inhibitors
    0.07
    Activations Density 0.009%

    No Known Activations