© 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. 32-TRANSCODER-HP
    7. 41940
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īåij¢
    -0.30
    emp
    -0.29
    访
    -0.26
    heet
    -0.26
    uits
    -0.25
    evin
    -0.25
    åĪ°æĿ¥
    -0.24
    ç»ĻæĤ¨
    -0.24
    -Sah
    -0.24
    .Pay
    -0.24
    POSITIVE LOGITS
     servi
    0.26
    å·´èı²
    0.25
    .Fields
    0.25
    éĨ¯
    0.23
    æľĪä¸ĭ
    0.23
    arios
    0.23
    åIJĸ
    0.23
     ansch
    0.23
     Nicar
    0.22
     使çĶ¨
    0.22
    Activations Density 0.001%

    No Known Activations