© 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. 4166
    Prev
    Next
    INDEX
    Explanations

    Ricardo, Verdean

    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
    ori
    -0.11
    olor
    -0.10
    æīĭåĨĮ
    -0.10
    åį°èĬ±
    -0.09
    趣
    -0.09
    绢
    -0.09
    èĭįçĻ½
    -0.09
    润æ»ij
    -0.09
    å¾Īä½İ
    -0.08
    oron
    -0.08
    POSITIVE LOGITS
    èĪįå¾Ĺ
    0.09
    asso
    0.09
    onte
    0.09
    asant
    0.08
    é£İåIJ¹
    0.08
    éĩįå·¥
    0.08
    dorf
    0.08
    бÑĥд
    0.08
    STONE
    0.08
    æ¿Ģæĥħ
    0.08
    Activations Density 0.006%

    No Known Activations