© 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. 31-TRANSCODER-HP
    7. 18870
    Prev
    Next
    INDEX
    Explanations

    coding and programming terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aza
    -0.28
     Dist
    -0.28
    EncodingException
    -0.27
    éħįå¥Ĺ
    -0.27
    break
    -0.26
    ache
    -0.26
    abo
    -0.26
    TRS
    -0.26
    ç¡ħ
    -0.25
    ило
    -0.25
    POSITIVE LOGITS
    æĽ´è¦ģ
    0.28
    runs
    0.26
     Low
    0.25
    vice
    0.24
    Low
    0.24
    misc
    0.23
    grave
    0.23
    æĽ´ä½İ
    0.23
    estone
    0.23
    ળ
    0.23
    Activations Density 0.058%

    No Known Activations