© 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. 3310
    Prev
    Next
    INDEX
    Explanations

    pointer

    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
    çĤĬ
    -0.11
    æıĦ
    -0.10
    æ°Ķæģ¯
    -0.10
    æIJ¦
    -0.10
    责任æĦŁ
    -0.09
    é¡¿
    -0.09
    æĹłæĥħ
    -0.09
    ation
    -0.09
    糧
    -0.09
    èķĻ
    -0.08
    POSITIVE LOGITS
    è·Ŀ
    0.10
    -INF
    0.08
    ç½ħ
    0.08
    IST
    0.08
    era
    0.08
     Tai
    0.08
    дин
    0.08
    ISK
    0.08
    Ä°K
    0.08
     unders
    0.07
    Activations Density 0.006%

    No Known Activations