© 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. 32628
    Prev
    Next
    INDEX
    Explanations

    watching people or 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
    躬
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
    æĴŀ
    -0.09
    éĢ¢
    -0.09
    éĺ»æŃ¢
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    éĢĤåºĶ
    -0.08
     überh
    -0.08
    å¦Ī
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    POSITIVE LOGITS
    _nth
    0.09
    åı°è´¦
    0.09
    anders
    0.08
    ľ
    0.08
    istes
    0.08
    missive
    0.08
    æĶ¿çŃĸæݪæĸ½
    0.08
    çľĭçĿĢ
    0.08
    Infinity
    0.08
    第ä¸Ģ家
    0.08
    Activations Density 0.019%

    No Known Activations