© 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. 63203
    Prev
    Next
    INDEX
    Explanations

    call upon, calling, draw

    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
     Gund
    -0.10
     Ñĥзн
    -0.10
    éĨĴ
    -0.10
    vu
    -0.09
    éĨĴ缮
    -0.08
    åĪĿæŃ¥
    -0.08
    tures
    -0.08
     Mun
    -0.08
    ä¸įæķ¢
    -0.08
    代表çĿĢ
    -0.08
    POSITIVE LOGITS
    è°ĥåĬ¨
    0.16
    åĬ¨åijĺ
    0.11
     Mobil
    0.10
    æķĻèĤ²èµĦæºIJ
    0.10
    éĽĦåİļ
    0.10
     reserves
    0.10
     Äijò
    0.10
     resources
    0.09
     draw
    0.09
    æ½ľèĥ½
    0.09
    Activations Density 0.094%

    No Known Activations