© 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. 9-TRANSCODER-HP
    7. 30397
    Prev
    Next
    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sockfd
    -0.27
    ç¾İçļĦ
    -0.25
     outlined
    -0.25
     scient
    -0.25
     Ä°l
    -0.24
    craft
    -0.24
    patterns
    -0.23
     wrong
    -0.23
    avigate
    -0.23
    ulen
    -0.23
    POSITIVE LOGITS
    æĢ»çĽij
    0.26
    æIJĢ
    0.26
    ertz
    0.25
    raph
    0.25
    Ñıн
    0.25
     extras
    0.25
    ç³»
    0.25
    ana
    0.25
    eno
    0.24
    ANE
    0.24
    Activations Density 3.673%

    No Known Activations