© 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. 33965
    Prev
    Next
    INDEX
    Explanations

    Academy Award

    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
    大家åĪĨ享
    -0.10
    æ²IJæµ´
    -0.09
    åĨ²çªģ
    -0.09
    antz
    -0.09
    éĢĶ
    -0.09
    uti
    -0.09
    æ§IJ
    -0.09
    ç¥ŀç§ĺ
    -0.08
    å´ĩé«ĺ
    -0.08
    ÙĨد
    -0.08
    POSITIVE LOGITS
    å¥ĸ
    0.10
     Patty
    0.10
    ssel
    0.09
    oire
    0.09
    GRP
    0.08
    pto
    0.08
    wide
    0.08
    æĭĨ
    0.08
     Moff
    0.08
     Tatto
    0.08
    Activations Density 0.004%

    No Known Activations