© 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. 23902
    Prev
    Next
    INDEX
    Explanations

    convinced or unlikely

    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
    æĢ»ç®Ĺ
    -0.08
    _tiles
    -0.08
     curt
    -0.08
     Lak
    -0.07
    åŁł
    -0.07
    _fitness
    -0.07
    èĩªæĿ¥
    -0.07
    åıijçİ°èĩªå·±
    -0.07
     Went
    -0.07
    ä¸įå¾Ĺ
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½åıijçĶŁ
    0.15
    é¢Ħæµĭ
    0.15
    åı¯èĥ½æĢ§
    0.15
    æĤ²è§Ĥ
    0.14
    ä¸įç¡®å®ļæĢ§
    0.14
    ä¹IJè§Ĥ
    0.13
    æľīåı¯èĥ½
    0.13
    æ½ľåľ¨
    0.13
    çļĦåı¯èĥ½æĢ§
    0.13
    å±ĬæŶ
    0.12
    Activations Density 0.078%

    No Known Activations