© 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. 57028
    Prev
    Next
    INDEX
    Explanations

    Slang terms

    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
    éĿ¢è²Į
    -0.28
    è¸Į
    -0.27
    undry
    -0.27
    zw
    -0.25
    ä¸įåħ·å¤ĩ
    -0.25
    ä¸įä¸Ĭ
    -0.25
    è¿Ļ家åħ¬åı¸
    -0.25
    ÙĬرة
    -0.25
    unky
    -0.24
    udas
    -0.24
    POSITIVE LOGITS
    style
    0.27
     google
    0.25
    active
    0.24
    ạt
    0.24
    /Internal
    0.24
    çĥŃ
    0.24
    森
    0.24
     Medical
    0.24
    çļĦæĹ¥åŃIJ
    0.23
    ä¸īä½į
    0.23
    Activations Density 0.007%

    No Known Activations