© 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. 6628
    Prev
    Next
    INDEX
    Explanations

    presentation, chart, comparison, emerging

    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
    iento
    -0.09
    踩
    -0.09
     Eb
    -0.08
    顽
    -0.08
    jer
    -0.08
    宫殿
    -0.08
    æľĢçĪ±
    -0.08
    fps
    -0.08
    Lou
    -0.08
    ám
    -0.08
    POSITIVE LOGITS
    çļ¿
    0.12
    éĻĢ
    0.11
    æĿ
    0.10
    好çľĭ
    0.09
    èįīåľ°
    0.09
    æĮª
    0.09
    é²ľèĬ±
    0.09
    æİĪäºĪ
    0.08
    ongyang
    0.08
     Schwe
    0.08
    Activations Density 0.095%

    No Known Activations