© 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. 34376
    Prev
    Next
    INDEX
    Explanations

    actions or processes

    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
    boom
    -0.09
    pers
    -0.09
    åįĥéĩĮ
    -0.08
     alike
    -0.08
    ergy
    -0.08
    为æĬĵæīĭ
    -0.08
    ä¹ĭå¿ĥ
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    æķ¬
    -0.08
    fos
    -0.08
    POSITIVE LOGITS
    åIJIJ
    0.09
    Doctrine
    0.09
    åħ¨åªĴä½ĵ
    0.09
    MLElement
    0.09
    åIJĪä¼Ļ人
    0.09
    ru
    0.09
    å¸ĤåľºéľĢæ±Ĥ
    0.08
    夺
    0.08
    éĿ©
    0.08
     Ñĩелов
    0.08
    Activations Density 0.088%

    No Known Activations