© 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. 19366
    Prev
    Next
    INDEX
    Explanations

    ot

    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
    ingo
    -0.32
    ansion
    -0.29
    aan
    -0.28
    soc
    -0.27
    oÅĽci
    -0.26
    _locator
    -0.26
    ext
    -0.25
    社ä¼ļåıijå±ķ
    -0.25
    建设åĴĮ
    -0.25
    ejs
    -0.25
    POSITIVE LOGITS
    æĬ¤
    0.27
    agen
    0.27
    eten
    0.26
    eti
    0.26
    æĮ¤
    0.25
    awan
    0.24
    大çļĦ
    0.24
    .inc
    0.24
    åŃ©
    0.24
    etype
    0.24
    Activations Density 0.009%

    No Known Activations