© 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. 63179
    Prev
    Next
    INDEX
    Explanations

    drugs

    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
    大å±Ģ
    -0.10
    iler
    -0.09
    deen
    -0.09
    å¹´ä¹ĭ
    -0.09
    æĤłä¹ħ
    -0.09
    izon
    -0.09
    ayas
    -0.09
    obar
    -0.09
    ipel
    -0.08
    ever
    -0.08
    POSITIVE LOGITS
    éŸ
    0.10
    sg
    0.09
    èĪħ
    0.09
    manship
    0.09
    aul
    0.08
    ë§Ŀ
    0.08
    主宰
    0.08
    èĨ³
    0.08
     Smy
    0.08
    éĢĿ
    0.08
    Activations Density 0.067%

    No Known Activations