© 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. 61433
    Prev
    Next
    INDEX
    Explanations

    Apple development frameworks

    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
    æĴ©
    -0.10
    ç©·
    -0.08
    ä¸ĥæĺŁ
    -0.08
     McM
    -0.08
    详
    -0.08
    åĦ¿
    -0.08
    æĤłæĤł
    -0.08
     Leipzig
    -0.08
     metro
    -0.07
    æľ«
    -0.07
    POSITIVE LOGITS
    é¦Ī
    0.11
    ä¸įåĩº
    0.09
    ivet
    0.09
    åIJŀ
    0.09
    berman
    0.09
    åĿı
    0.09
    usercontent
    0.09
    å®īåĢį
    0.09
    åĿıäºĨ
    0.09
    .apple
    0.09
    Activations Density 0.278%

    No Known Activations