© 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. 50757
    Prev
    Next
    INDEX
    Explanations

    probability of picking

    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
    obuf
    -0.09
    olean
    -0.08
    çĿĢçľ¼äºİ
    -0.08
    ä½ij
    -0.08
    第ä¸īæĸ¹
    -0.08
    åĭ¤
    -0.08
    èŀįåIJĪåıijå±ķ
    -0.08
    é¢Ľ
    -0.08
    ä¸įåħģ许
    -0.08
    quirrel
    -0.08
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.10
    é¢Ĥ
    0.10
     erv
    0.10
    åĩºçİ°
    0.09
    è½
    0.09
    è¿Ļéĥ¨åĪĨ
    0.09
    æĪij说
    0.09
    icity
    0.09
    åĩºçı¾
    0.09
    ÅĦ
    0.09
    Activations Density 0.039%

    No Known Activations