© 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. 31-TRANSCODER-HP
    7. 17752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĢ¼
    -0.26
    æĪ¿
    -0.26
    代
    -0.25
     References
    -0.24
    faces
    -0.24
    è´¦
    -0.24
     normally
    -0.24
    gov
    -0.24
     references
    -0.23
    ROOM
    -0.23
    POSITIVE LOGITS
    urat
    0.33
    rat
    0.33
     Rat
    0.27
    å§Ĵ
    0.27
    ARDS
    0.26
    æµĴ
    0.26
    orget
    0.26
    _BAD
    0.25
    ahan
    0.25
    åĦ¿
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.