© 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. 39473
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories comfort

    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
    ilon
    -0.09
    éĭª
    -0.09
    rent
    -0.08
    etrain
    -0.08
    å°ıå°ıçļĦ
    -0.08
    éĵº
    -0.08
    æīĭå¥Ĺ
    -0.08
     Dust
    -0.08
    åħħåĢ¼
    -0.08
    .fake
    -0.08
    POSITIVE LOGITS
    èĮ¸
    0.10
    æķ´ä¸ªäºº
    0.09
    _STATES
    0.09
    çŁ¥éģĵèĩªå·±
    0.09
    zzo
    0.09
    ä¸į失
    0.08
    grim
    0.08
     EXPRESS
    0.08
    ä¿¡æģ¯æľįåĬ¡
    0.08
    =Value
    0.08
    Activations Density 0.010%

    No Known Activations