© 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. 57936
    Prev
    Next
    INDEX
    Explanations

    condiments, ingredients, parts of words

    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
    imagem
    -0.10
    requ
    -0.10
    å¹´éĻIJ
    -0.09
    åĺ§
    -0.09
    æ¯ħåĬĽ
    -0.09
    æŀIJ
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    adal
    -0.09
    çĶ·åŃ©
    -0.09
     bicy
    -0.08
    POSITIVE LOGITS
    zo
    0.09
    åĬ«
    0.08
    thouse
    0.08
    æ´»è·ĥ
    0.08
    çŃīåĬŁèĥ½
    0.08
    æı¡æīĭ
    0.08
    rico
    0.08
    ä¸įä¸Ĭ
    0.08
    æľī幸
    0.08
    eper
    0.08
    Activations Density 0.006%

    No Known Activations