© 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. 39649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĬ¶
    -0.30
    ctal
    -0.29
    STYPE
    -0.27
    æ´»è·ĥ
    -0.26
     Bronx
    -0.26
    Decl
    -0.26
     Decl
    -0.24
    çĬ¶åĨµ
    -0.24
     Booth
    -0.24
    è¹Ń
    -0.24
    POSITIVE LOGITS
     MISS
    0.27
    DOC
    0.25
     narr
    0.25
    çĶ¥
    0.25
    erÃŃa
    0.25
     servants
    0.25
    IFn
    0.24
    ãģ¾ãģĽ
    0.24
    æıIJä¾Ľä¼ĺè´¨
    0.24
     craw
    0.24
    Activations Density 0.064%

    No Known Activations

    This feature has no known activations.