© 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. 18746
    Prev
    Next
    INDEX
    Explanations

    computer code context

    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
    Keeper
    -0.30
    _sets
    -0.28
    Compact
    -0.27
    ä¿ĿæĮģ
    -0.27
     Po
    -0.26
    compact
    -0.26
     Compact
    -0.26
     keeping
    -0.26
    isti
    -0.26
    被害
    -0.26
    POSITIVE LOGITS
    fer
    0.27
    è¯Ľ
    0.26
     tcb
    0.25
    rig
    0.24
    æ´ª
    0.24
    çłĶåĪ¤
    0.24
    ategy
    0.23
    .isDirectory
    0.23
     Libre
    0.23
    è¡£
    0.23
    Activations Density 0.006%

    No Known Activations