© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7413
    Prev
    Next
    INDEX
    Explanations

    polishing pads, cerium oxide, hundred years

    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
     Wings
    -0.09
    éĴı
    -0.09
    åıĭæĥħ
    -0.08
    èĽĩ
    -0.08
    ilo
    -0.08
    ç¼Ĩ
    -0.08
    æĮĩæĮ¥
    -0.08
    oley
    -0.08
    ç¿ħ
    -0.08
    _spacing
    -0.08
    POSITIVE LOGITS
    磨
    0.16
    åīĥ
    0.13
    æīĵ磨
    0.12
    çł¥
    0.10
    ä¸ĢéĿ¢
    0.10
    ä¸ĢåIJį
    0.10
    è²Ĥ
    0.10
    ç²¾çĽĬæ±Ĥç²¾
    0.10
    éĻ·
    0.09
    ä¿®
    0.09
    Activations Density 0.117%

    No Known Activations