© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107301
    Prev
    Next
    INDEX
    Explanations

    currency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iti
    -0.28
    verty
    -0.27
    ewood
    -0.25
    éºĭ
    -0.25
    orpion
    -0.25
     fif
    -0.25
    ronic
    -0.24
    elts
    -0.24
     Golf
    -0.24
    é£İæļ´
    -0.23
    POSITIVE LOGITS
    éĻ¢éĻ¢éķ¿
    0.26
    为主é¢ĺ
    0.26
    åıªä¼ļ
    0.25
    为主线
    0.25
    ùng
    0.24
    éĥ½ä¸įä¼ļ
    0.24
    侯
    0.24
    ãģ°ãģĭãĤĬ
    0.23
     coordinate
    0.23
    /release
    0.23
    Activations Density 0.049%

    No Known Activations