© 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. 107007
    Prev
    Next
    INDEX
    Explanations

    vitamin

    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
    Negative Logits
    模
    -0.29
    åĵģ
    -0.28
    æĬ¹
    -0.27
    路线
    -0.26
    UILT
    -0.25
    _USAGE
    -0.25
    èı±
    -0.25
    ò
    -0.25
    åĬŀå®ŀäºĭ
    -0.25
    tain
    -0.25
    POSITIVE LOGITS
    ereo
    0.29
    IRS
    0.26
    çļĦåĨ³å¿ĥ
    0.26
    .ms
    0.26
    .mo
    0.25
    ãģĵãģ¨
    0.25
     sẵn
    0.25
    acet
    0.25
    .kr
    0.24
    交代
    0.24
    Activations Density 0.336%

    No Known Activations