© 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. 10071
    Prev
    Next
    INDEX
    Explanations

    visit and destination

    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
    jsc
    -0.09
    zek
    -0.08
    åįķåĵģ
    -0.08
    ji
    -0.08
    _DRV
    -0.08
    交
    -0.08
    æ¯ıéĢ¢
    -0.07
    èĭ±æīį
    -0.07
    ainter
    -0.07
    ç»ĵç®Ĺ
    -0.07
    POSITIVE LOGITS
    磮
    0.10
    çĭłæĬĵ
    0.09
    ä¸Ģ身
    0.09
    çıī
    0.09
    åĴĮæĬĢæľ¯
    0.09
    æĿ¥è®¿
    0.09
    å¨ģæħij
    0.09
    访éĹ®
    0.09
    论è¯ģ
    0.09
    å¼łè´´
    0.09
    Activations Density 0.030%

    No Known Activations