© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50354
    Prev
    Next
    INDEX
    Explanations

    reporting speech or requests

    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
    lient
    -0.09
     воÑĤ
    -0.09
    Checks
    -0.09
    checks
    -0.09
    å¿ĥæĢĿ
    -0.08
    UME
    -0.08
    .cv
    -0.08
    ç
    -0.08
    ær
    -0.08
     UNUSED
    -0.08
    POSITIVE LOGITS
    ëĿ½
    0.09
    åijĬè¯ī大家
    0.09
    è¦ģæĬĬ
    0.09
    èĩªå·±åĸľæ¬¢
    0.09
    ç»Ļä»ĸ们
    0.08
    ŧ
    0.08
    大家éĥ½åľ¨
    0.08
    äºĨä¸Ģåı¥
    0.08
    èĬ¸
    0.08
    åħij
    0.08
    Activations Density 0.044%

    No Known Activations