© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    adjective describing a noun

    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
    ÑģоÑĢ
    -0.10
    ISR
    -0.09
    æµij
    -0.09
     Townsend
    -0.08
    LTR
    -0.08
    说èĩªå·±
    -0.08
    以èī²
    -0.08
    ansi
    -0.08
    å¹´ä¸ŃåĽ½
    -0.08
    caffold
    -0.08
    POSITIVE LOGITS
    人æ°ijæľįåĬ¡
    0.09
    第ä¸īåŃ£åº¦
    0.08
    建åĨĽ
    0.08
    æŀī
    0.08
    éģĹ
    0.08
    headed
    0.08
    aus
    0.08
    èĽ´
    0.08
    view
    0.08
    ude
    0.08
    Activations Density 0.130%

    No Known Activations