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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 31195
    Prev
    Next
    INDEX
    Explanations

    till

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đánh
    -0.07
    _NEW
    -0.07
    autiful
    -0.07
    ustry
    -0.07
     אוה
    -0.07
    azed
    -0.07
     anew
    -0.07
     borç
    -0.07
     구
    -0.06
     an
    -0.06
    POSITIVE LOGITS
    גברים
    0.08
     till
    0.07
    辦
    0.07
    Light
    0.07
    كف
    0.07
     inflater
    0.07
     rent
    0.07
    ------↵↵
    0.07
     screams
    0.07
    FileDialog
    0.07
    Activations Density 0.004%

    No Known Activations