© 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. 19220
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
     evaluate
    -0.67
     generate
    -0.65
     distribute
    -0.64
     solve
    -0.63
     execute
    -0.63
    etrize
    -0.63
     integrate
    -0.63
     modify
    -0.62
     analyze
    -0.62
     apply
    -0.62
    POSITIVE LOGITS
    è¿Ľåħ¥äºĨ
    0.36
    åĽŀåĪ°äºĨ
    0.35
    åĨ³å®ļäºĨ
    0.34
    éĻįä½İäºĨ
    0.33
    æıIJé«ĺäºĨ
    0.33
    çĤ¹äºĨçĤ¹å¤´
    0.32
    带æĿ¥äºĨ
    0.32
    çķĻä¸ĭäºĨ
    0.32
    éĢłæĪIJäºĨ
    0.32
    æĿ¥åĪ°äºĨ
    0.31
    Activations Density 5.371%

    No Known Activations