© 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. 26800
    Prev
    Next
    INDEX
    Explanations

    court records and app archive

    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
    éĽı
    -0.11
    蹬
    -0.10
    å°Ĭ
    -0.09
    ç¾Į
    -0.09
    æ·ĺæ±°
    -0.09
    çĪĨåĩº
    -0.08
    代è¨Ģ人
    -0.08
    æĭħ
    -0.08
    妻
    -0.08
    åIJįèªī
    -0.08
    POSITIVE LOGITS
    移éĢģ
    0.10
    空çĻ½
    0.09
    æ¦Ľ
    0.09
     ASCII
    0.09
    çĻ¾åĪĨ
    0.09
    åľŃ
    0.09
    å½ĵæĻļ
    0.08
    æĹ¥è®¯
    0.08
    ront
    0.08
    abal
    0.08
    Activations Density 0.202%

    No Known Activations