© 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. 10117
    Prev
    Next
    INDEX
    Explanations

    potential action

    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
    ä¸į容
    -0.11
    ä¸įæľį
    -0.10
    ä¸įéĶĻ
    -0.09
    éĿŀ常好çļĦ
    -0.09
    éĿŀ常é«ĺ
    -0.09
    å·®ä¸įå¤ļ
    -0.09
    éĿŀ常å¤ļ
    -0.08
    ä¸įå¿ĺ
    -0.08
    ingle
    -0.08
    没éĶĻ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
     anything
    0.13
    è´µ
    0.13
    çĶŁæĢķ
    0.13
    åĽłä¸ºä»ĸ
    0.13
    ä¹Łä¸įæķ¢
    0.12
    åĽłä¸ºå®ĥ
    0.12
     Anything
    0.11
     anymore
    0.11
    åĽłä¸ºæĪij们
    0.11
    Activations Density 0.085%

    No Known Activations