© 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. 48761
    Prev
    Next
    INDEX
    Explanations

    access to private or protected pages

    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
    ä¸įèµ·
    -0.10
    容纳
    -0.10
    é©°
    -0.09
    åĪ°åľº
    -0.09
    åĨ¤
    -0.09
    åľ¨çİ°åľº
    -0.09
    ATIC
    -0.08
    é¢Ģ
    -0.08
    celed
    -0.08
    æ²®
    -0.08
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.13
    æĮij
    0.12
     protected
    0.10
    æķıæĦŁ
    0.10
    涩
    0.10
    ariat
    0.10
     Protected
    0.09
    æĽ´æ·±
    0.09
    protected
    0.09
    ä¸ĵå±ŀ
    0.09
    Activations Density 0.117%

    No Known Activations