© 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. 31444
    Prev
    Next
    INDEX
    Explanations

    thank you for your answer/help/response

    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
    åIJĦ个çݯèĬĤ
    -0.11
    åij¨è½¬
    -0.10
    æĺ¯éĿŀ
    -0.09
    åĩłå®¶
    -0.09
    æĪijåıªæĺ¯
    -0.09
    orama
    -0.09
    åĽŀäºĭ
    -0.09
    亮çĤ¹
    -0.09
    åģļçļĦäºĭæĥħ
    -0.08
    èĵĿåĽ¾
    -0.08
    POSITIVE LOGITS
    çIJĨ解åĴĮ
    0.10
    çĸijéĹ®
    0.09
    ç»Ń
    0.09
    ä¿Ĥ
    0.09
    zi
    0.09
    amd
    0.08
    é¦Ĩ
    0.08
    çĺ¦
    0.08
    åĵį
    0.08
    ĻĤ
    0.08
    Activations Density 0.014%

    No Known Activations