© 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. 14-TRANSCODER-HP
    7. 39425
    Prev
    Next
    INDEX
    Explanations

    use of resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _war
    -0.27
    éĻ¢
    -0.25
    odo
    -0.25
    æ¯Ľ
    -0.25
    éĶĭ
    -0.25
    çĥĪ
    -0.25
     Easter
    -0.25
    hits
    -0.24
     Peel
    -0.24
    èĬ¬
    -0.24
    POSITIVE LOGITS
    unnable
    0.27
    .Nullable
    0.26
     bug
    0.24
    _STRUCTURE
    0.23
    ASURE
    0.23
    åIJĦç±»
    0.23
    players
    0.23
    .addListener
    0.23
    à¸Īา
    0.23
    emand
    0.23
    Activations Density 0.497%

    No Known Activations