© 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. 20-TRANSCODER-HP
    7. 140687
    Prev
    Next
    INDEX
    Explanations

    Programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _subtype
    -0.31
    祸
    -0.28
    âĹĢ
    -0.28
    .ca
    -0.28
    åŃIJåħ¬åı¸
    -0.27
     subtype
    -0.26
    holes
    -0.26
    à¹Īà¸Ńย
    -0.26
    agina
    -0.25
    embro
    -0.25
    POSITIVE LOGITS
     accord
    0.27
    uhn
    0.27
    utable
    0.27
    æ²»çIJĨä½ĵç³»
    0.25
    gm
    0.25
    èĴĻ
    0.25
    åIJ¬å¾Ĺ
    0.25
    è§Ĩé¢ij
    0.25
     Horn
    0.24
    nton
    0.24
    Activations Density 9.570%

    No Known Activations