© 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. 96808
    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĩºåħ¥
    -0.25
    òng
    -0.25
    åĩŃåĢŁ
    -0.25
     daddy
    -0.25
    士
    -0.24
    è¶ĭåIJij
    -0.24
    æĺ¯åĽłä¸º
    -0.24
    éĻĭ
    -0.24
    ä¾Ŀæīĺ
    -0.24
    ìłľ
    -0.24
    POSITIVE LOGITS
    าว
    0.26
     inline
    0.26
     Martian
    0.24
     RNG
    0.23
    igion
    0.23
    |#
    0.23
    [âĢ¦
    0.23
    Mounted
    0.23
    BN
    0.23
    inline
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.