© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    building components

    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
    çĭ¬å®¶
    -0.10
    éļĶ
    -0.09
    ynet
    -0.09
    æĥ®
    -0.09
    ephy
    -0.09
    交代
    -0.08
     беÑĢ
    -0.08
    arrant
    -0.08
    æīĽ
    -0.08
     Escort
    -0.08
    POSITIVE LOGITS
    信访
    0.10
    æݾ
    0.09
    åı¹æģ¯
    0.09
    åĬĿ
    0.09
    å¿ĥè¡Ģ
    0.09
    çłĸ
    0.09
    æħ°
    0.09
    èĻŀ
    0.08
    iffs
    0.08
    è´¢æĶ¿éĥ¨
    0.08
    Activations Density 0.305%

    No Known Activations