© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21548
    Prev
    Next
    INDEX
    Explanations

    time duration (second, minute, moment)

    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
    ä¸ī天
    -0.11
    ä¸Ģ天
    -0.11
    åĩłå¤©
    -0.10
    麻çĥ¦
    -0.09
    ä¸Ģè¶Ł
    -0.09
    éĶ¢
    -0.08
    äºĨäºĽ
    -0.08
    ä¸Ģ个æľĪ
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    ä¸Ģ段æŶéĹ´
    -0.08
    POSITIVE LOGITS
    èģĶ
    0.09
    ìĶ©
    0.09
    èī¯å¿ĥ
    0.09
    让人们
    0.09
     Ñĥзн
    0.09
    nish
    0.08
    ÙĦØ©
    0.08
    /moment
    0.08
    ç¡ķ
    0.08
    ritis
    0.08
    Activations Density 0.026%

    No Known Activations