© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9507
    Prev
    Next
    INDEX
    Explanations

    religious obligation and redemption

    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
     fid
    -0.08
    訴
    -0.08
     Madison
    -0.08
    NING
    -0.08
    formed
    -0.08
    ning
    -0.08
    å½¢æĪIJçļĦ
    -0.08
    è¯ī
    -0.07
     rak
    -0.07
    nap
    -0.07
    POSITIVE LOGITS
    é«ĺçŃī
    0.11
    é«ĺæ°´å¹³
    0.10
    å»Ľ
    0.10
    åĹŁ
    0.09
    èĹģ
    0.09
    åı£æ°´
    0.09
    лей
    0.09
    пÑĢоÑģ
    0.09
    éĿ´
    0.09
    éĿ¢ç²ī
    0.09
    Activations Density 0.041%

    No Known Activations