© 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. 62004
    Prev
    Next
    INDEX
    Explanations

    healthy volunteerscrossover studydogs reacted

    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
    æĿĢ
    -0.10
    å¹¼
    -0.09
    鸾
    -0.09
    ä¿®
    -0.09
    dest
    -0.09
    åĪĹ举
    -0.09
    çĦ¦
    -0.08
    slaught
    -0.08
    ãĤ¤ãĥĪ
    -0.08
    @stop
    -0.08
    POSITIVE LOGITS
    çĶ·å¥³
    0.10
    æ¯ı个人çļĦ
    0.09
    åIJĥ饱
    0.09
    contr
    0.09
    æ¸ħæ·¡
    0.08
    éŨå¤ĸ
    0.08
    éļ¾åıĹ
    0.08
    åħ¨æĹ¥åĪ¶
    0.08
    è¯ķ
    0.08
    ä½ĵéªĮ
    0.08
    Activations Density 0.602%

    No Known Activations