© 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. 41629
    Prev
    Next
    INDEX
    Explanations

    action/process

    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
     fresh
    -0.28
    ãĥĥãĥī
    -0.28
    èī¯
    -0.27
    лÑĮн
    -0.27
    á»ijn
    -0.26
    uja
    -0.26
    omb
    -0.26
     espect
    -0.26
    声éģĵ
    -0.25
    лен
    -0.24
    POSITIVE LOGITS
    è¿Ļ个è¡Įä¸ļ
    0.28
    blank
    0.26
    STALL
    0.25
    éĻIJè´Ń
    0.25
    çĪ±åĽ½ä¸»ä¹ī
    0.25
    çĻ½æ²Ļ
    0.24
    为ä»Ģä¹Īè¦ģ
    0.24
    illard
    0.24
    éŨæĪ·ç½ijç«Ļ
    0.24
     Armstrong
    0.23
    Activations Density 0.297%

    No Known Activations