© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56754
    Prev
    Next
    INDEX
    Explanations

    code or markup fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iske
    -0.29
    åıĺå¾ĹæĽ´
    -0.29
     actual
    -0.29
    .hm
    -0.28
     instrumental
    -0.28
    绣ä¸Ģ
    -0.28
    igli
    -0.27
    æľºä¼ļ
    -0.27
     fucking
    -0.27
     uniform
    -0.27
    POSITIVE LOGITS
    ipzig
    0.25
    æĺİæľĿ
    0.24
    odate
    0.24
     cravings
    0.24
    aidu
    0.24
    indh
    0.23
    alist
    0.23
    loon
    0.23
     tedious
    0.23
    å¯ĵ
    0.23
    Activations Density 0.800%

    No Known Activations