© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    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
    ä¸įæĪIJ
    -0.30
    OfMonth
    -0.28
     pret
    -0.26
    éŵ
    -0.25
     treasurer
    -0.25
    ä¼ļéķ¿
    -0.24
     Treasurer
    -0.24
    rom
    -0.24
    çĿĢä»ĸ
    -0.24
    овиÑĩ
    -0.23
    POSITIVE LOGITS
    anker
    0.27
    ypass
    0.27
    hd
    0.27
    [].
    0.27
    ethod
    0.26
    TEL
    0.25
    MET
    0.25
    cent
    0.25
     sou
    0.25
    ãĥ¯ãĥ¼ãĤ¯
    0.24
    Activations Density 0.006%

    No Known Activations