© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 54550
    Prev
    Next
    INDEX
    Explanations

    seeking applicants for offers

    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
    haven
    -0.09
    æīij
    -0.09
     form
    -0.08
     formally
    -0.08
    onis
    -0.08
    ãģ£ãģ¦ãģĦãģı
    -0.07
    Form
    -0.07
    cia
    -0.07
     prod
    -0.07
    (skip
    -0.07
    POSITIVE LOGITS
    èģĶç³»æĸ¹å¼ı
    0.11
    åĭ¿
    0.11
    请èģĶç³»
    0.10
    èģĶç³»
    0.10
     конÑĤакÑĤ
    0.10
    è¯ļæĦı
    0.10
     CONTACT
    0.10
    æľ¬æĬ¥
    0.10
    alls
    0.10
     poste
    0.10
    Activations Density 0.083%

    No Known Activations