© 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. 7317
    Prev
    Next
    INDEX
    Explanations

    list items and actions

    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
    /or
    -0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.09
    æīĢ带æĿ¥çļĦ
    -0.08
    æĽ´ä½ķåĨµ
    -0.08
    æīĢä»¥åľ¨
    -0.08
    èĢĮä¸Ķ
    -0.08
    彬
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
    resp
    -0.08
    åħ¶æ¬¡æĺ¯
    -0.08
    POSITIVE LOGITS
    	TokenName
    0.10
    åħ¥ãĤĬ
    0.10
    inent
    0.09
    odule
    0.09
    ophile
    0.09
    äºĭ
    0.09
    åĩĨåħ¥
    0.09
    /licenses
    0.08
    åĩĨ
    0.08
    SOR
    0.08
    Activations Density 0.237%

    No Known Activations