© 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. 16984
    Prev
    Next
    INDEX
    Explanations

    drawing, writing, marking, or doodling

    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
    onium
    -0.10
    足足
    -0.09
    ìĦŃ
    -0.09
    mana
    -0.09
    æ´²
    -0.09
    apat
    -0.09
    æ³½
    -0.08
    .interpolate
    -0.08
    agne
    -0.08
    书éĿ¢
    -0.08
    POSITIVE LOGITS
    åªĴä½ĵ
    0.09
    æĮģä¹ħ
    0.09
    æĮ½
    0.09
    egg
    0.08
    ç»
    0.08
    orm
    0.08
    姿åĬ¿
    0.08
    åªĴä½ĵæĬ¥éģĵ
    0.08
    æľºæ²¹
    0.08
    ä»ĵ
    0.08
    Activations Density 0.052%

    No Known Activations