© 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. 18140
    Prev
    Next
    INDEX
    Explanations

    fluid components or solutions

    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
     tran
    -0.09
    sel
    -0.08
    è¿Ľç¨ĭ
    -0.08
    åħ¨ç¨ĭ
    -0.08
    ä¸Ģæł¹
    -0.08
    ational
    -0.08
    abra
    -0.08
    æľĿé²ľ
    -0.08
    ä¸ĢæĬĬ
    -0.08
    æĦŁåĬ¨
    -0.08
    POSITIVE LOGITS
    æ±ģ
    0.10
    ä¿Ĺ称
    0.09
    ä¸Ńæľī
    0.09
    æĽ´éĢĤåIJĪ
    0.09
    forth
    0.08
    ê°Ī
    0.08
    Locator
    0.08
    详ç»Ĩä»ĭç»į
    0.08
    é¼ĭ
    0.08
    AGR
    0.08
    Activations Density 0.372%

    No Known Activations