© 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. 11107
    Prev
    Next
    INDEX
    Explanations

    thoughtand realized

    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
    çĻĸ
    -0.08
     mes
    -0.08
    mes
    -0.08
    害
    -0.08
    毫ä¸į
    -0.08
    ä¸Ģ缴éĥ½æĺ¯
    -0.08
    åľĪåŃIJ
    -0.08
    çĺ´
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    æĥ³ä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    æĶ¾å¼ĥäºĨ
    0.14
    ç®ĹäºĨ
    0.11
    顾èĻij
    0.11
     realized
    0.11
     realised
    0.11
    太大
    0.10
    ä¸į对
    0.10
    ä¸įç¡®å®ļ
    0.10
    åıįè¿ĩæĿ¥
    0.10
    æĥ³åĪ°
    0.09
    Activations Density 0.112%

    No Known Activations