© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62149
    Prev
    Next
    INDEX
    Explanations

    oh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sincer
    -0.09
    å·´å·´
    -0.08
     à¹Ĩ
    -0.08
    ech
    -0.08
    æ·±çŁ¥
    -0.08
    à¹Ĩ
    -0.08
    çıĬçijļ
    -0.08
    ulan
    -0.08
    een
    -0.08
    ies
    -0.08
    POSITIVE LOGITS
     ÑģлÑĥÑĩ
    0.09
    å·ħ
    0.09
    rego
    0.09
    кÑĢаÑĤ
    0.08
    /vendors
    0.08
    é¢ł
    0.08
    andles
    0.08
    æĪij们认为
    0.08
    mute
    0.08
    ç«Ł
    0.08
    Activations Density 0.007%

    No Known Activations