© 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. 48068
    Prev
    Next
    INDEX
    Explanations

    type of

    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
    éĤ£ä¸Ģ
    -0.10
    éĥ¨åĪĨ
    -0.10
    ä¸ĢçĤ¹çĤ¹
    -0.10
    ئ
    -0.10
    ä¸Ģé»ŀ
    -0.09
    éģ´éĢī
    -0.09
    ä¸ĢçĤ¹
    -0.09
    .ol
    -0.09
    ä¸Ģ大æī¹
    -0.09
    éĤ£æ¬¡
    -0.09
    POSITIVE LOGITS
    äºŁ
    0.09
    æĻ®éģįåŃĺåľ¨
    0.08
    çĤī
    0.08
     Ped
    0.08
    çĽĪ
    0.08
    éĥ½èĥ½å¤Ł
    0.07
    è¡Ĺ头
    0.07
     these
    0.07
     Sor
    0.07
    æľºåĬ¨
    0.07
    Activations Density 0.146%

    No Known Activations