© 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. 62988
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    æĸ¯å¡Ķ
    -0.11
    æľ¬ç½ijç«Ļ
    -0.10
     иÑģпол
    -0.09
    ÑĤай
    -0.09
    åīįèĢħ
    -0.09
    éĢħ
    -0.09
    èİ«æĸ¯ç§ij
    -0.09
    sons
    -0.09
    Ùİا
    -0.09
    é¾Ļæ³ī
    -0.09
    POSITIVE LOGITS
    ulary
    0.09
    oner
    0.09
     Cur
    0.08
    ondo
    0.08
    æħij
    0.08
    åľ¨ä¸ĢæĹģ
    0.08
    combe
    0.08
    zilla
    0.08
    æ°Ķæģ¯
    0.07
    igest
    0.07
    Activations Density 0.887%

    No Known Activations