© 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. 39572
    Prev
    Next
    INDEX
    Explanations

    supplying resources to cities/users

    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
    {{$
    -0.32
    lain
    -0.27
    <?=$
    -0.25
    .Gravity
    -0.25
    cia
    -0.25
    //{{
    -0.25
    <?=
    -0.25
    ichten
    -0.25
    factory
    -0.25
    è¯Ń
    -0.24
    POSITIVE LOGITS
    onds
    0.26
    è§ī
    0.25
    -hours
    0.25
    ооÑĢ
    0.25
    äº²çľ¼
    0.24
    -answer
    0.24
    好åĩłä¸ª
    0.24
    anson
    0.24
    -spot
    0.24
    shire
    0.23
    Activations Density 1.921%

    No Known Activations