© 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. 38942
    Prev
    Next
    INDEX
    Explanations

    complaints and reports

    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
    tested
    -0.09
    åĬłä¹ĭ
    -0.09
     Remote
    -0.09
    stin
    -0.08
    cies
    -0.08
    çĭĤ
    -0.08
    éģ¥
    -0.08
    çģ¾
    -0.08
    éģ¥æݧ
    -0.08
    殿åłĤ
    -0.08
    POSITIVE LOGITS
    æĬķè¯ī
    0.16
    åıĹçIJĨ
    0.15
    ç«ĭæ¡Ī
    0.13
    è¯īæ±Ĥ
    0.12
    ç»´æĿĥ
    0.12
    çĶ³è¯ī
    0.12
    亲èĩª
    0.12
     complaint
    0.12
     complaints
    0.12
    信访
    0.11
    Activations Density 0.064%

    No Known Activations