© 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. 29690
    Prev
    Next
    INDEX
    Explanations

    version numbers like 2.0

    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
    京
    -0.09
    lass
    -0.09
    gross
    -0.09
     hem
    -0.08
    çŁ¾
    -0.08
    ahan
    -0.08
    ias
    -0.08
    íĿ¥
    -0.08
    æ´Ĺ澡
    -0.08
    è´©
    -0.08
    POSITIVE LOGITS
    æ°Ķæģ¯
    0.10
    æŃ»åİ»
    0.09
    bler
    0.09
    -era
    0.09
    PLEX
    0.09
    orst
    0.09
    _UNLOCK
    0.09
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    izzle
    0.09
     \@
    0.09
    Activations Density 0.007%

    No Known Activations