© 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. 61059
    Prev
    Next
    INDEX
    Explanations

    wet pussy

    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
    é¢Ĩ
    -0.13
    éłĺ
    -0.12
    èĦĸåŃIJ
    -0.10
     Featuring
    -0.09
    ç©¿ä¸Ĭ
    -0.09
    åĹĵåŃIJ
    -0.09
    çľīæ¯Ľ
    -0.09
    à¸ģาย
    -0.09
    踮
    -0.09
    ç©¿çĿĢ
    -0.09
    POSITIVE LOGITS
    uzzle
    0.08
    atur
    0.08
    æĹĹå¸ľ
    0.08
    _interfaces
    0.08
    æ»ŀ
    0.08
    abay
    0.08
    ç²¾åįİ
    0.08
    åĪºæ¿Ģ
    0.07
    hare
    0.07
    éĺµ
    0.07
    Activations Density 0.019%

    No Known Activations