© 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. 30070
    Prev
    Next
    INDEX
    Explanations

    grammar

    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
    TAIL
    -0.09
    atar
    -0.09
    æĹ¥è®°
    -0.09
    ãĥŃãĥ¼
    -0.09
    å®ī举
    -0.09
    tail
    -0.09
    ×Ļ×ķ
    -0.08
    å·¥ä½ľä»»åĬ¡
    -0.08
    åѦä¸ļ
    -0.08
    AIL
    -0.08
    POSITIVE LOGITS
    ware
    0.10
    æݾ
    0.09
    æĶ¸
    0.09
    伶
    0.09
    acia
    0.09
    eting
    0.09
    Invariant
    0.09
    éĴľ
    0.09
    sexual
    0.09
    ikh
    0.08
    Activations Density 0.007%

    No Known Activations