© 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. 109550
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Wiki
    -0.27
    LEM
    -0.24
    ØŃÙĬ
    -0.24
     recalled
    -0.24
     vá»įng
    -0.24
    çŁ¿ä¸ļ
    -0.24
    ãĥģãĤ§
    -0.24
    è¯Ħæµĭ
    -0.23
     crypto
    -0.23
    è¿Ļæĺ¯ä¸Ģ个
    -0.23
    POSITIVE LOGITS
    åľ¨çİ°åľº
    0.31
    label
    0.31
    lite
    0.30
    ä¸ĢéĿ¢
    0.30
     label
    0.29
    inson
    0.29
    /classes
    0.26
    åħ¨å¤©
    0.26
     subclass
    0.26
    -label
    0.25
    Activations Density 0.925%

    No Known Activations