© 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. 59025
    Prev
    Next
    INDEX
    Explanations

    night

    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
    第ä¸ī个
    -0.10
    rah
    -0.10
    失信
    -0.09
    强迫
    -0.09
    иÑĨе
    -0.09
    inky
    -0.08
    ç»ŀ
    -0.08
    inus
    -0.08
    olly
    -0.08
    .OutputStream
    -0.08
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.09
    extras
    0.09
     bè
    0.09
    è¸ŀ
    0.09
    ç¿©
    0.09
    åŬ
    0.08
     Sham
    0.08
    uffs
    0.08
    尾巴
    0.08
    ISM
    0.08
    Activations Density 0.006%

    No Known Activations