© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    filling data

    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
    PropertyParams
    -0.10
    羣æŃ£åģļåĪ°
    -0.09
    æ£ĭçīĮ游æĪı
    -0.09
    åĴ¥
    -0.08
    天èĬ±
    -0.08
    	TokenName
    -0.08
    éļ¾çĤ¹
    -0.08
    ButtonTitles
    -0.08
    ç²¾åįİ
    -0.08
     Brewer
    -0.08
    POSITIVE LOGITS
    è¸Į
    0.10
     XYZ
    0.08
    ä¹Ŀæ±Ł
    0.08
    \u
    0.08
    à¹Ĥà¸Ī
    0.08
     [âĢ¦]
    0.08
    ฯ
    0.08
    alta
    0.08
     \"
    0.08
    <br
    0.07
    Activations Density 0.904%

    No Known Activations