© 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. 43449
    Prev
    Next
    INDEX
    Explanations

    try/trying

    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
    为æĤ¨
    -0.30
     yourself
    -0.29
    ãģĤãģªãģŁãģ®
    -0.28
     yourselves
    -0.28
    æĤ¨çļĦ
    -0.28
    ä½łçļĦ
    -0.28
     Your
    -0.27
     your
    -0.27
    your
    -0.27
     бÑĭÑĤÑĮ
    -0.27
    POSITIVE LOGITS
    ——
    0.42
    —
    0.40
     —
    0.39
    ---
    0.38
    âĢķâĢķ
    0.36
     ---
    0.36
     since
    0.35
     –
    0.33
     in
    0.33
    —in
    0.33
    Activations Density 0.007%

    No Known Activations