© 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. 63684
    Prev
    Next
    INDEX
    Explanations

    blooming flowers

    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
    оÑĤоÑĢ
    -0.10
    æµ·å°Ķ
    -0.10
    /rc
    -0.09
     Flake
    -0.09
    æ¦ķ
    -0.09
     Blaze
    -0.09
     Cynthia
    -0.08
     Gilbert
    -0.08
    umin
    -0.08
     Cout
    -0.08
    POSITIVE LOGITS
     bouquet
    0.09
     Kund
    0.09
    atron
    0.09
    æĢĴ
    0.09
    æ³£
    0.09
    isu
    0.09
     arrangements
    0.09
     arrangement
    0.09
     vase
    0.08
     sắp
    0.08
    Activations Density 0.054%

    No Known Activations