© 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. 48864
    Prev
    Next
    INDEX
    Explanations

    stimulation causing effects

    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
    æ²¥
    -0.10
    oling
    -0.09
    æĸĩåĮĸ交æµģ
    -0.09
    åIJĮç±»
    -0.09
    ç²ķ
    -0.09
    adic
    -0.08
    åĴ¬
    -0.08
     Tie
    -0.08
     drivers
    -0.08
    ç°ĥ
    -0.08
    POSITIVE LOGITS
    ÑĢеÑģ
    0.10
    主æµģ
    0.09
    ãĤĴä¸İãģĪ
    0.08
    agini
    0.08
    ç²®
    0.08
    æĿª
    0.08
     strokes
    0.08
    ewis
    0.08
    æŁĶæĢ§
    0.08
    åĨį说
    0.08
    Activations Density 0.011%

    No Known Activations