© 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. 24-TRANSCODER-HP
    7. 149389
    Prev
    Next
    INDEX
    Explanations

    bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     déco
    -0.27
     düzenlen
    -0.25
    bedo
    -0.25
    åĪĨæµģ
    -0.24
    dden
    -0.24
    Enumerable
    -0.24
     skulls
    -0.23
     Beacon
    -0.23
    readonly
    -0.23
     Laundry
    -0.23
    POSITIVE LOGITS
    fluid
    0.28
    ester
    0.27
     algorithm
    0.27
     fluid
    0.27
    говоÑĢ
    0.26
    åĴĮæĬĢæľ¯
    0.26
    ä¸ĢèĤ¡
    0.26
    è°IJ
    0.25
    çĶ¥
    0.25
    åľ¨æ¸¸æĪıä¸Ń
    0.25
    Activations Density 0.128%

    No Known Activations