© 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. 24-TRANSCODER-HP
    7. 151410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å°±çŁ¥éģĵ
    -0.26
     interpolated
    -0.25
     Conversion
    -0.24
     nominate
    -0.24
    /INFO
    -0.24
    -inf
    -0.23
    被æĬĵ
    -0.23
     Dere
    -0.23
    iddy
    -0.23
     implication
    -0.23
    POSITIVE LOGITS
     theirs
    0.30
    çĦĬ
    0.28
     grind
    0.27
    ä¼¼
    0.26
    ç¨į
    0.26
    婦
    0.26
     hers
    0.26
     unw
    0.25
     demand
    0.25
    onder
    0.25
    Activations Density 0.117%

    No Known Activations

    This feature has no known activations.