© 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. 30554
    Prev
    Next
    INDEX
    Explanations

    bump, green, moving, play, tire

    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
    è¢«åĽ°
    -0.08
    çķĻå®Ī
    -0.08
    abin
    -0.08
    éĤ£æ¬¡
    -0.08
    赦
    -0.07
    绦
    -0.07
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.07
     loyal
    -0.07
     Legisl
    -0.07
    Chain
    -0.07
    POSITIVE LOGITS
    mia
    0.10
     عÙĨÙĩا
    0.09
    ç¶ĵ常
    0.09
    ä»İåݻ年
    0.09
    ä¿£
    0.09
     chá»Ĺ
    0.09
    зи
    0.09
     ÑģÑĤÑĥд
    0.09
    éķł
    0.09
    åľ¨åľ°ä¸Ĭ
    0.09
    Activations Density 0.059%

    No Known Activations