© 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. 62679
    Prev
    Next
    INDEX
    Explanations

    effects on

    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
     ÑģÑĤо
    -0.10
    çĶ¨æĿ¥
    -0.09
    ISON
    -0.09
     Tales
    -0.09
    为äºĨ让
    -0.09
    olson
    -0.09
    çļĦæĹ¶ä»£
    -0.09
     tales
    -0.09
    å¾ĭ
    -0.09
     tal
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.12
    æķ´ä¸ª
    0.11
     elect
    0.09
    å¾Ĺèµ·
    0.09
     Mell
    0.09
    çļĦ人æĿ¥è¯´
    0.09
    æķ´åĢĭ
    0.09
    æĪij们çļĦ
    0.08
    åIJĦé¡¹å·¥ä½ľ
    0.08
    åİŁæľīçļĦ
    0.08
    Activations Density 0.133%

    No Known Activations