© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    Lab Systems, football clubs, company names

    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
    裾
    -0.09
    æĻ¾
    -0.09
    uly
    -0.09
    itched
    -0.08
    بش
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    æķijåij½
    -0.08
    çĽĺæ´»
    -0.08
    éĿŀçī©è´¨
    -0.08
    èĻij
    -0.08
    POSITIVE LOGITS
    巨人
    0.09
    usercontent
    0.09
    ׳×ķת
    0.08
    åĨ³å¿ĥ
    0.08
    antium
    0.08
    /Grid
    0.08
    azer
    0.08
     ÑĥкÑĢа
    0.08
    举
    0.08
    (tk
    0.08
    Activations Density 0.710%

    No Known Activations