© 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. 23-TRANSCODER-HP
    7. 23701
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kaar
    -0.27
    etyl
    -0.27
    cales
    -0.27
    æ¶İ
    -0.26
    éĸĵãģ«
    -0.25
    führung
    -0.25
    llx
    -0.25
    diÄŁimiz
    -0.24
    undy
    -0.24
     пеÑĢемен
    -0.24
    POSITIVE LOGITS
    æķ´çIJĨ
    0.30
     full
    0.29
    Full
    0.28
    ull
    0.26
    -desc
    0.26
    .vo
    0.26
     Full
    0.26
     breaking
    0.25
    ULL
    0.25
    ä¸Ĭåįĩ
    0.25
    Activations Density 0.002%

    No Known Activations