© 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. 19262
    Prev
    Next
    INDEX
    Explanations

    talking

    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
    CPP
    -0.26
     nu
    -0.25
    éĮ¯
    -0.25
    ðĿijŀ
    -0.24
    ickets
    -0.24
    ÑħÑĢан
    -0.23
    åĩºãģĹãģ¦
    -0.23
    ippo
    -0.23
    æĽĻ
    -0.23
    çijĽ
    -0.23
    POSITIVE LOGITS
     speak
    0.82
     speaking
    0.80
     spoke
    0.68
     speaks
    0.66
     talk
    0.63
     Speak
    0.63
     spoken
    0.61
     Speaking
    0.61
     talking
    0.59
    -speaking
    0.58
    Activations Density 4.692%

    No Known Activations