© 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. 56898
    Prev
    Next
    INDEX
    Explanations

    drug names

    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
    ä¹ĸä¹ĸ
    -0.10
    ç³ħ
    -0.09
     Ones
    -0.09
    å¤ĦåĪĨ
    -0.09
    à¹Ĥ
    -0.09
    èĢģ人家
    -0.08
     vl
    -0.08
    æ¶Īéĺ²å®īåħ¨
    -0.08
    éĺĴ
    -0.08
     indiscrim
    -0.08
    POSITIVE LOGITS
    è¢Ĥ
    0.09
    åij½è¿IJ
    0.09
    ENDED
    0.09
     suit
    0.08
    ä¸įéĶĪ
    0.08
    å¼Ģå°ģ
    0.08
    ä¿ĿèįIJ
    0.08
    æĪĮ
    0.08
    rovers
    0.08
    portlet
    0.08
    Activations Density 0.141%

    No Known Activations