© 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. 48025
    Prev
    Next
    INDEX
    Explanations

    dental restorations and treatments

    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
    Output
    -0.09
    _INITIALIZ
    -0.09
    æĪijä¸įçŁ¥éģĵ
    -0.09
    NEL
    -0.09
     èĭ¥è¦ģ
    -0.09
    å·¡åĽŀ
    -0.09
    éĺĥ
    -0.09
    å¥ĩå¼Ĥ
    -0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.09
    è¢Ń
    -0.08
    POSITIVE LOGITS
    ampo
    0.10
    ÑĦоÑĢ
    0.10
    çĻ½éĵ¶
    0.09
    çĮĿ
    0.09
     اÙĦض
    0.09
     Dwight
    0.08
    çѦ
    0.08
     Tro
    0.08
    ortal
    0.08
    (tb
    0.08
    Activations Density 0.142%

    No Known Activations