© 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. 21606
    Prev
    Next
    INDEX
    Explanations

    Copyright year

    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
    lik
    -0.11
    æIJħ
    -0.09
    æħİ
    -0.09
    骸
    -0.09
    äºĮåŃĹ
    -0.09
     Carp
    -0.09
    anger
    -0.08
    inky
    -0.08
    linky
    -0.08
    utex
    -0.08
    POSITIVE LOGITS
    诣
    0.10
    å§ĭäºİ
    0.09
    pch
    0.09
    æ³ķå®ļ
    0.09
    èĥ½åĬĽå¼º
    0.08
    Nib
    0.08
    ä¸ĭåįķ
    0.08
    çļĦèĥĮåIJİ
    0.08
    åĪ°è¿ĻéĩĮ
    0.08
    (Call
    0.08
    Activations Density 0.028%

    No Known Activations