© 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. 19395
    Prev
    Next
    INDEX
    Explanations

    say "s" words

    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
    ãģĦãģ¾ãģĻ
    -0.33
    ãģĦãģŁ
    -0.31
    ãģĦãģı
    -0.29
    ãģŁãĤģãģ«
    -0.28
    ãģıãĤĮ
    -0.28
    inois
    -0.27
    oci
    -0.27
    ãģĦãģ¾ãģĹãģŁ
    -0.26
    ãģ§ãģį
    -0.25
    keh
    -0.25
    POSITIVE LOGITS
    sm
    0.97
    sg
    0.89
    sw
    0.87
    ss
    0.85
    sc
    0.82
    sd
    0.80
    sp
    0.79
    sto
    0.79
    sth
    0.79
    stype
    0.78
    Activations Density 68.701%

    No Known Activations