© 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. 62323
    Prev
    Next
    INDEX
    Explanations

    lotion, cream, wash, formulations

    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
     daunting
    -0.09
    물ìĿĦ
    -0.09
    REW
    -0.09
    ä»ĵ
    -0.09
    xdc
    -0.08
    ç¾¹
    -0.08
     sight
    -0.08
    clid
    -0.08
    ords
    -0.08
    hart
    -0.08
    POSITIVE LOGITS
    ting
    0.09
    cel
    0.09
    æĸ¹åľĨ
    0.09
    naires
    0.09
     зан
    0.09
    âĹī
    0.09
    neau
    0.09
    åŃIJéĩĮ
    0.09
    armed
    0.08
    chy
    0.08
    Activations Density 0.001%

    No Known Activations