© 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. 5090
    Prev
    Next
    INDEX
    Explanations

    style and appearance

    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
    æīĵéĢļ
    -0.10
    ä¼Ĺ
    -0.10
    è°Ģ
    -0.09
    éĵī
    -0.09
    ä¹IJ趣
    -0.09
    åIJīåĪ©
    -0.09
    太ä¹ħ
    -0.09
    çļĦä¹IJ趣
    -0.08
    åŀĴ
    -0.08
    娱ä¹IJ
    -0.08
    POSITIVE LOGITS
    æ°Ķè´¨
    0.14
    ç©¿æIJŃ
    0.12
    大æĸ¹
    0.12
    ä¼ĺéĽħ
    0.10
    佩æĪ´
    0.10
    ä»İ容
    0.10
    æķ£åıij
    0.10
    _checked
    0.09
    åĩºå¸Ń
    0.09
    çĦ¦çĤ¹
    0.09
    Activations Density 0.092%

    No Known Activations