© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16581
    Prev
    Next
    INDEX
    Explanations

    standalone, alone, separately

    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
    Negative Logits
    _VOID
    -0.09
    usic
    -0.09
    shit
    -0.09
    é»ĺ
    -0.09
     облаÑģÑĤи
    -0.08
    èĮħ
    -0.08
     conven
    -0.08
    ((&
    -0.08
    åĮºåĨħ
    -0.08
    æ¯ķ
    -0.08
    POSITIVE LOGITS
    åįķçĭ¬
    0.25
     standalone
    0.21
    çĭ¬ç«ĭ
    0.21
    çį¨ç«ĭ
    0.17
     ÑģамоÑģÑĤоÑı
    0.15
    -alone
    0.15
    èĦ±ç¦»
    0.14
    åѤç«ĭ
    0.13
    çĭ¬èĩª
    0.13
     Independ
    0.13
    Activations Density 0.309%

    No Known Activations