© 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. 151175
    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
    Âł
    -0.27
     cord
    -0.27
     math
    -0.26
    ebin
    -0.25
     future
    -0.25
     put
    -0.25
     stick
    -0.25
     mes
    -0.25
    âĢ
    -0.24
    ####
    -0.24
    POSITIVE LOGITS
    导åIJij
    0.31
     ridden
    0.27
    ä¸įéĻIJ
    0.27
    èµĦæºIJåħ±äº«
    0.27
    -folder
    0.26
    '][]
    0.25
    ä¼ijæģ¯
    0.25
    ToF
    0.25
    æľĿçĿĢ
    0.24
    azon
    0.24
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.