© 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. 107182
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĽĺ
    -0.28
    hof
    -0.28
     Acc
    -0.27
    ague
    -0.27
    å¼ķ
    -0.26
    婵
    -0.26
    åģ¥åº·
    -0.26
    é¹Ĺ
    -0.26
    ÙĤÙħ
    -0.25
    jm
    -0.25
    POSITIVE LOGITS
    _study
    0.27
    è´²
    0.26
    åı¯æĥ³èĢĮ
    0.25
    masters
    0.25
    ä½»
    0.24
     wel
    0.24
    æł·åŃIJ
    0.24
    å¥ĭè¿Ľ
    0.24
    -fin
    0.24
    磨
    0.23
    Activations Density 0.953%

    No Known Activations

    This feature has no known activations.