© 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. 32610
    Prev
    Next
    INDEX
    Explanations

    Orlando

    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
    lessly
    -0.11
    Ñıв
    -0.09
    -lang
    -0.09
    .timezone
    -0.09
    èµŀèµı
    -0.09
    룰
    -0.09
    yled
    -0.08
    楼
    -0.08
    çīį
    -0.08
    leased
    -0.08
    POSITIVE LOGITS
    ascript
    0.09
    æľī许å¤ļ
    0.09
    CHIP
    0.09
    ä¸ĭåįĬå¹´
    0.09
    led
    0.09
    ender
    0.09
    etta
    0.09
    ../../../
    0.09
    大巴
    0.09
    athering
    0.08
    Activations Density 0.007%

    No Known Activations