© 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. 23661
    Prev
    Next
    INDEX
    Explanations

    Tata words and their applications

    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
    est
    -0.10
    -être
    -0.10
    èĩªå¦Ĥ
    -0.09
    raries
    -0.09
    ened
    -0.09
    ร
    -0.09
     ÙĪاÙĦع
    -0.08
    аÑĢам
    -0.08
    ennen
    -0.08
    é¢Į
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸Ĭ
    0.10
    ìķ¼
    0.10
    ÑĩаÑģ
    0.09
     Pork
    0.09
    è¨Ģè¡Į
    0.09
    tempts
    0.08
     bare
    0.08
    ék
    0.08
    tees
    0.08
    vik
    0.08
    Activations Density 0.006%

    No Known Activations