© 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. 34983
    Prev
    Next
    INDEX
    Explanations

    meiosinmaister

    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
    -0.12
    sted
    -0.09
    sher
    -0.08
    ãģĬãĤĪãģ³
    -0.08
    à¸Ńà¸ĩ
    -0.07
    -0.07
    ery
    -0.07
     sector
    -0.07
    ãģ¾ãģŁãģ¯
    -0.07
     RF
    -0.07
    POSITIVE LOGITS
    éĿŀ常çļĦ
    0.10
    ç»ıå¼ĢåĮº
    0.10
    æİī
    0.10
    åIJİå¤ĩ
    0.10
    ided
    0.09
    ãģ¤ãģij
    0.09
    owered
    0.09
    çļĦåIJĮåѦ
    0.09
    illance
    0.09
    å·´å·´
    0.09
    Activations Density 0.303%

    No Known Activations