© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38105
    Prev
    Next
    INDEX
    Explanations

    dates, times, and numbers

    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
    æ©IJ
    -0.07
    以ä¸ĭæĺ¯
    -0.07
    _VF
    -0.07
     disarm
    -0.06
    .Generated
    -0.06
    ——
    -0.06
    â½
    -0.06
     QObject
    -0.06
     —
    -0.06
     ’
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸īà¸ŀ
    0.09
    stdafx
    0.09
    à¹ĭ
    0.09
    _:*
    0.09
    à¸Ĥà¸Ļา
    0.09
    à¸Ħะà¹ģà¸Ļ
    0.09
    สามาร
    0.08
    emin
    0.08
    onaut
    0.08
    rew
    0.08
    Activations Density 1.104%

    No Known Activations