© 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. 21829
    Prev
    Next
    INDEX
    Explanations

    condemn, criticized, frowned

    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¸įå¦Ĥ
    -0.10
    è¿ĺä¸įå¦Ĥ
    -0.09
    holm
    -0.09
    èĥ½è¾¾åĪ°
    -0.08
    便åĪ©
    -0.08
    æĶ¾æĿ¾
    -0.08
    åıįèĢĮ
    -0.08
    éĺ´éĺ³
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    å¹³çŃī
    -0.08
    POSITIVE LOGITS
    è°´è´£
    0.18
    æĥĭ
    0.12
    严åİīæīĵåĩ»
    0.11
    åĪ¶æŃ¢
    0.11
    æīĵåĩ»
    0.11
    çĹĽ
    0.11
    æ·ĺæ±°
    0.11
    åİĮæģ¶
    0.10
    å«ī
    0.10
    æģ¶
    0.10
    Activations Density 0.096%

    No Known Activations