© 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. 30-TRANSCODER-HP
    7. 94890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĻ¶
    -0.32
    ART
    -0.31
    æĮģ
    -0.28
    anks
    -0.27
    鸳
    -0.26
    æĮģæľī
    -0.26
    -mask
    -0.25
    оваÑĢ
    -0.25
    immer
    -0.25
    lords
    -0.24
    POSITIVE LOGITS
    =default
    0.28
     sorte
    0.27
     sort
    0.25
    Sensitive
    0.24
    åºľ
    0.24
    iros
    0.23
    /google
    0.23
    FIT
    0.23
    europ
    0.23
    '))->
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.