© 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. 26719
    Prev
    Next
    INDEX
    Explanations

    YMCA, YM, YP

    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
    æľ¬ç½ij
    -0.10
    undy
    -0.09
    主åĬĽ
    -0.09
    åĵķ
    -0.09
    综åIJĪæĢ§
    -0.09
    éŀĭåŃIJ
    -0.09
    éŀĭ
    -0.09
    ãĥ©ãĥ³ãĤŃãĥ³ãĤ°
    -0.09
    eted
    -0.08
    à¹ĩà¸Ļ
    -0.08
    POSITIVE LOGITS
    æĺĤ
    0.11
    éĶ»çĤ¼
    0.09
    ç«łç¨ĭ
    0.09
    -library
    0.08
    é¹ħ
    0.08
    chor
    0.08
    обоÑĢ
    0.08
    é«ĺåĩº
    0.08
    brero
    0.08
    à¸ģาย
    0.08
    Activations Density 0.007%

    No Known Activations