© 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. 54832
    Prev
    Next
    INDEX
    Explanations

    placed or inserted

    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
    éĤ£è¾¹
    -0.10
    èĭ¦éļ¾
    -0.09
    _ABORT
    -0.08
    çĹĽèĭ¦
    -0.08
    åĽł
    -0.08
    bach
    -0.08
    rik
    -0.08
    åľ¨ä»ĸçļĦ
    -0.08
    auf
    -0.08
    omm
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.12
    交ç»Ļ
    0.09
    ç½®äºİ
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    çļĦæķ´ä½ĵ
    0.09
    æķ´ä¸ª
    0.09
    warts
    0.09
     overall
    0.08
    éĴ¤
    0.08
    ä¸ĬæĬ¥
    0.08
    Activations Density 0.209%

    No Known Activations