© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53878
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨèĩªå·±çļĦ
    -0.25
    _consts
    -0.25
    ewart
    -0.24
    ä¸Ģæĸ¹éĿ¢
    -0.24
    åİŁåĽłä¹ĭä¸Ģ
    -0.24
    askan
    -0.23
    aska
    -0.23
    liqu
    -0.23
     supper
    -0.23
    ÑİÑĢ
    -0.23
    POSITIVE LOGITS
    -week
    0.35
    -
    0.35
    cents
    0.34
    -degree
    0.34
    -l
    0.33
    -inch
    0.33
    -ring
    0.33
    -million
    0.33
    -point
    0.33
    -frame
    0.33
    Activations Density 0.043%

    No Known Activations