© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8217
    Prev
    Next
    INDEX
    Explanations

    but, so, if, or, while

    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
     Valent
    -0.09
    æ´Ĵ
    -0.08
    \n
    -0.08
    oids
    -0.08
     Ike
    -0.08
    åĩłä¹İ
    -0.08
    lim
    -0.08
    åĩłä¹İæīĢæľī
    -0.07
    oid
    -0.07
    Berry
    -0.07
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.17
    åĽłä¸ºå¥¹
    0.13
    åĽłä¸ºæĪij们
    0.13
    æĪĸ许æĺ¯
    0.13
    æŁIJç§į
    0.11
    åı¯èĥ½æĺ¯
    0.11
    åĽłä¸ºåľ¨
    0.11
    ä¼ļä¸įä¼ļ
    0.11
    ä½Ĩ她
    0.11
     ÐĴедÑĮ
    0.11
    Activations Density 0.274%

    No Known Activations