© 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. 62759
    Prev
    Next
    INDEX
    Explanations

    press conference

    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
    侥幸
    -0.09
    éļ¹
    -0.09
    ç¢Į
    -0.09
    éĺ²ç©º
    -0.08
    æ²¥
    -0.08
    èĥĮä¸Ĭ
    -0.08
    olu
    -0.08
    åī©
    -0.08
    åħ¨åĬĽä»¥èµ´
    -0.08
    æĬķåħ¥åĪ°
    -0.08
    POSITIVE LOGITS
    enti
    0.09
    wnd
    0.09
    зн
    0.09
    éĽį
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
    	TokenName
    0.09
    -worthy
    0.09
    waters
    0.08
    俨
    0.08
    vice
    0.08
    Activations Density 0.005%

    No Known Activations