© 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. 34247
    Prev
    Next
    INDEX
    Explanations

    free software and tools

    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
    thumbnails
    -0.09
    (OP
    -0.09
    ï¿¥
    -0.09
    วà¸ĩ
    -0.09
    erchant
    -0.08
    ä¾ij
    -0.08
    à¸Ńà¸Ķ
    -0.08
    ç³Ł
    -0.08
    åĥ®
    -0.08
    orro
    -0.08
    POSITIVE LOGITS
    /free
    0.12
     indis
    0.09
    ä¸ĭæĿ¥
    0.09
    iec
    0.08
    ä¹ħä¹ħ
    0.08
    äºĨä¸ĭæĿ¥
    0.08
    owy
    0.08
    poses
    0.08
    phin
    0.08
    æī¿æĭħ
    0.08
    Activations Density 0.049%

    No Known Activations