© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22418
    Prev
    Next
    INDEX
    Explanations

    cost increases

    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
    è¶Ĭ好
    -0.09
    è¯ī
    -0.09
    æľį
    -0.09
    ç¿İ
    -0.08
    ISON
    -0.08
    çĸ²
    -0.08
    consts
    -0.08
     Trom
    -0.08
     IReadOnly
    -0.08
    èĩªè±ª
    -0.08
    POSITIVE LOGITS
    éĶĻè¿ĩ
    0.16
    缺å°ij
    0.12
    éĶĻè¿ĩäºĨ
    0.11
    éģĹæ¼ı
    0.11
    缺
    0.10
    æİ¨è¿Ł
    0.10
    æ»ŀåIJİ
    0.10
     depr
    0.10
    æľįåĬ¡æ°´å¹³
    0.10
    æĨĭ
    0.09
    Activations Density 0.207%

    No Known Activations