© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 935
    Prev
    Next
    INDEX
    Explanations

    take care of

    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
    éģĤ
    -0.09
    è®°è½½
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    èħ¾
    -0.09
    èIJ½ä¸ĭ
    -0.09
    eks
    -0.08
    è¤IJ
    -0.08
    .netbeans
    -0.08
    è¡Įç¨ĭ
    -0.08
    æºĥ
    -0.08
    POSITIVE LOGITS
    aring
    0.11
    人æĿĥ
    0.10
    fully
    0.10
    èĪ¸
    0.09
    SERVER
    0.09
    quire
    0.09
    igor
    0.09
    bots
    0.08
    ARING
    0.08
    åħ®
    0.08
    Activations Density 0.004%

    No Known Activations