© 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. 53622
    Prev
    Next
    INDEX
    Explanations

    thinking about past events

    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
    éĹ»
    -0.09
    ç³Ĭ
    -0.09
     Fired
    -0.08
    èģŀ
    -0.08
    ç´¯
    -0.08
     shock
    -0.08
    åıĶ
    -0.08
    æĥħå½¢
    -0.08
    å¼Ĥ
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    POSITIVE LOGITS
    çIJ¢ç£¨
    0.14
    æĥ³çĿĢ
    0.13
    å¦Ĥä½ķåİ»
    0.12
    ðŁĴŃ
    0.12
    çºłç»ĵ
    0.12
    å¿ĥæĢĿ
    0.11
    èĤ´
    0.11
    æĢĿ绪
    0.11
    宵
    0.11
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    Activations Density 0.064%

    No Known Activations