© 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. 31709
    Prev
    Next
    INDEX
    Explanations

    area disparity levels

    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
    èµı
    -0.09
    çĸı导
    -0.09
    åĿļ强
    -0.09
    BOOT
    -0.09
    æĮij
    -0.08
     Salem
    -0.08
    å¤Ħç½®
    -0.08
    ä¸įéĻIJ
    -0.08
    akh
    -0.08
    .easy
    -0.08
    POSITIVE LOGITS
    æĬķå½±
    0.10
    imates
    0.09
    人åı£
    0.09
    èĩ§
    0.09
    portrait
    0.09
    ç½ijæĬķ
    0.09
    棱
    0.09
    è¡ħ
    0.09
    详ç»Ĩä»ĭç»į
    0.09
    inte
    0.08
    Activations Density 0.155%

    No Known Activations