© 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. 26511
    Prev
    Next
    INDEX
    Explanations

    alcoholic beverages and patients

    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
    ively
    -0.10
    cape
    -0.09
    ä¾Ľç»Ļ侧
    -0.09
    fulness
    -0.09
    lider
    -0.09
    lands
    -0.09
    wing
    -0.09
    亲çĪ±
    -0.09
    ä¹ĭåĬĽ
    -0.08
    çĶŁåij½åĬĽ
    -0.08
    POSITIVE LOGITS
    ÑģÑĮ
    0.11
    碼
    0.09
    omon
    0.08
    ì¡´
    0.08
    bling
    0.08
    ä¸ĩäºĭ
    0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.08
    pleted
    0.08
    饮åĵģ
    0.08
     bells
    0.08
    Activations Density 0.038%

    No Known Activations