© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    Th

    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
     COPYING
    -0.29
    yne
    -0.26
    ling
    -0.26
    ipel
    -0.26
    ickle
    -0.26
    èĥį
    -0.25
    æIJģ
    -0.25
    li
    -0.25
     reliably
    -0.24
    úde
    -0.24
    POSITIVE LOGITS
     Stats
    0.27
    Cod
    0.26
     comps
    0.26
     mosaic
    0.25
     иÑģполни
    0.25
    ç«¥
    0.25
     Comp
    0.24
    Comp
    0.24
    缤
    0.24
    razione
    0.24
    Activations Density 0.006%

    No Known Activations