© 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. 48718
    Prev
    Next
    INDEX
    Explanations

    optical mouse

    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
    isko
    -0.12
    çĸ
    -0.10
    éĴ¢æĿ¿
    -0.10
    éªĤ
    -0.09
    çīµå¼ķ
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    éŃģ
    -0.09
    éħ£
    -0.09
    ç¬ĥ
    -0.09
     META
    -0.09
    POSITIVE LOGITS
    forc
    0.09
    åįĥ
    0.08
    -inst
    0.08
    稿
    0.08
    lect
    0.08
    maal
    0.08
     Ink
    0.08
    ç²®
    0.08
    åij¨äºĮ
    0.08
     hå
    0.08
    Activations Density 0.113%

    No Known Activations