© 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. 57494
    Prev
    Next
    INDEX
    Explanations

    alone, single, solo

    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
    ynn
    -0.09
    è°ĥåīĤ
    -0.09
     MMA
    -0.09
    缸éĢļ
    -0.08
    æ¬ł
    -0.08
     vice
    -0.08
    elight
    -0.08
    phet
    -0.08
    ç²¾
    -0.08
    éģŀ
    -0.08
    POSITIVE LOGITS
    çĭ¬èĩª
    0.22
     alone
    0.21
    ä¸Ģ个人
    0.19
    alone
    0.19
     Alone
    0.18
    ä¸Ģ人
    0.18
     solo
    0.17
    çĭ¬
    0.16
    ä¸ĢåĢĭ人
    0.15
     lone
    0.15
    Activations Density 0.089%

    No Known Activations