© 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. 29782
    Prev
    Next
    INDEX
    Explanations

    random selection from lists

    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
    åIJĦèĩªçļĦ
    -0.10
    鸦
    -0.09
    ëĶ°
    -0.09
     xét
    -0.08
    çļĦ好
    -0.08
    èģĺ
    -0.08
    髦
    -0.08
     Nim
    -0.08
    èĩªè§ī
    -0.08
    åĩĽ
    -0.08
    POSITIVE LOGITS
    åĩĨ
    0.10
    æµ·æ°´
    0.09
    禧
    0.09
    ERIC
    0.09
    åħ¬æŃ£
    0.09
    pole
    0.08
     Revel
    0.08
    endl
    0.08
     cerv
    0.08
    é£İéĻ©ç®¡çIJĨ
    0.08
    Activations Density 0.023%

    No Known Activations