© 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. 55555
    Prev
    Next
    INDEX
    Explanations

    ligand binding, fatty acids

    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
    åij¨ä¸Ģ
    -0.09
     Kur
    -0.09
    éģĹ
    -0.09
    é»ĺ
    -0.09
    spread
    -0.09
    hread
    -0.09
    纤
    -0.09
    åĪ©çī©
    -0.09
    mares
    -0.08
    åij¨äºĶ
    -0.08
    POSITIVE LOGITS
    ä¿İ
    0.11
    å¤ĸæĿ¥
    0.10
     present
    0.09
    åħ¥ä¾µ
    0.09
    æ¶Įåħ¥
    0.09
    zan
    0.09
    aster
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    ä¿¡åı·
    0.08
     pu
    0.08
    Activations Density 0.657%

    No Known Activations