© 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. 106915
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    dere
    -0.32
    egrity
    -0.28
    etimes
    -0.28
     dew
    -0.27
     dere
    -0.27
     Dere
    -0.26
     spoil
    -0.26
    建档
    -0.26
    Depth
    -0.26
    ally
    -0.26
    POSITIVE LOGITS
    éĺĬ
    0.29
    æľĢ大åĮĸ
    0.28
    ŀæĢ§
    0.27
    udu
    0.25
     ent
    0.25
    é«ĺæĸ°åĮº
    0.25
     acos
    0.25
    ensen
    0.25
    åŃĹ第
    0.25
     Stamford
    0.24
    Activations Density 1.075%

    No Known Activations