© 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. 39795
    Prev
    Next
    INDEX
    Explanations

    recognize or acknowledge

    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
    说æĺ¯
    -0.09
    ude
    -0.09
    osis
    -0.08
    毫ä¸įçĬ¹è±«
    -0.08
    åı·ç§°
    -0.08
    解éĩĬ
    -0.08
     Tam
    -0.08
     pir
    -0.08
    Tam
    -0.08
    arella
    -0.08
    POSITIVE LOGITS
     rằng
    0.11
    认è¯ĨåĪ°
    0.11
    æĦıè¯ĨåĪ°
    0.11
     bahwa
    0.10
     keen
    0.09
    /OR
    0.09
    åĬŀ好
    0.09
    keletal
    0.09
    orado
    0.08
    ë´ī
    0.08
    Activations Density 0.021%

    No Known Activations