© 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. 41955
    Prev
    Next
    INDEX
    Explanations

    Foreign characters

    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
    ç®Ĺ
    -0.27
    ypy
    -0.27
    Ymd
    -0.26
    riors
    -0.26
     Crawford
    -0.26
    rek
    -0.25
    erson
    -0.25
     cuk
    -0.25
     Kad
    -0.24
    undos
    -0.24
    POSITIVE LOGITS
    åijĬè¯ī她
    0.33
    ç»Ļ她
    0.31
    Ha
    0.27
    空ä¸Ń
    0.27
    她çļĦ
    0.27
    æĬĬ她
    0.26
    åĽ½åĢº
    0.26
    她æĺ¯
    0.25
     smo
    0.25
    acts
    0.25
    Activations Density 0.001%

    No Known Activations