© 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. 23720
    Prev
    Next
    INDEX
    Explanations

    between or through

    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
     rid
    -0.11
    æ¤į
    -0.10
    _DUMP
    -0.10
    èįĴ
    -0.09
    ãĥ¼ãĥ«
    -0.09
    ãĤ«ãĥ«
    -0.09
    åĢ¨
    -0.09
    骧
    -0.09
    æĺı
    -0.09
    åľºä¸Ĭ
    -0.08
    POSITIVE LOGITS
    éĹ´éļĻ
    0.11
    æ¼ı
    0.10
    èĩªä¸»
    0.10
    ç¼ĿéļĻ
    0.09
    éļĻ
    0.09
     gaps
    0.08
    æ¼ıæ´ŀ
    0.08
    jac
    0.08
     cracks
    0.08
    enie
    0.08
    Activations Density 0.035%

    No Known Activations