© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35906
    Prev
    Next
    INDEX
    Explanations

    license blocks

    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
     dÃłng
    -0.10
    ŀ
    -0.09
    人éĥ½
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    ../
    -0.08
    æ¤ħ
    -0.08
    建ç«ĭåģ¥åħ¨
    -0.08
    ãĢħ
    -0.08
    wear
    -0.08
    obb
    -0.08
    POSITIVE LOGITS
    yles
    0.10
    onte
    0.10
    å¿ĥæĥħ
    0.09
    èĪ¬çļĦ
    0.09
    erer
    0.09
    害ç¾ŀ
    0.09
    imb
    0.09
    aire
    0.09
    yle
    0.09
    IAS
    0.09
    Activations Density 0.146%

    No Known Activations