© 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. 23581
    Prev
    Next
    INDEX
    Explanations

    moss names and entities

    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
    èįīæ¡Ī
    -0.10
    atos
    -0.10
    pics
    -0.10
    ç¼¢
    -0.09
    åĪ¸
    -0.09
    æľīæĿĥ
    -0.09
    ÑĤÑĢ
    -0.09
    çģ¶
    -0.09
    åĮ»åѦéĻ¢
    -0.09
    ture
    -0.09
    POSITIVE LOGITS
    side
    0.09
    ambique
    0.09
    itori
    0.08
    迹象
    0.08
    iness
    0.08
    ford
    0.08
    gage
    0.08
    è´²
    0.08
    dale
    0.08
    à¸Ĺาà¸ĩ
    0.08
    Activations Density 0.003%

    No Known Activations