© 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. 10622
    Prev
    Next
    INDEX
    Explanations

    cancelled or postponed events

    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
    èĤī
    -0.09
    agnostics
    -0.09
    æ¯ıå¹´éĥ½
    -0.08
    èĥľåĪ©
    -0.08
    åĸī
    -0.08
    ä»ĸå·²ç»ı
    -0.08
    è§ģåĪ°
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    overe
    -0.08
    POSITIVE LOGITS
    åľºåľ°
    0.13
    åľº
    0.11
    åıĸæ¶Ī
    0.11
    é¢Ŀå¤ĸ
    0.10
    å½ĵ天
    0.10
    æİ¨è¿Ł
    0.10
    åł´
    0.09
     cancellation
    0.09
     extra
    0.09
    ä¸įå¾Ĺä¸į
    0.09
    Activations Density 0.080%

    No Known Activations