© 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. 17177
    Prev
    Next
    INDEX
    Explanations

    Joseph followed by names

    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
    foot
    -0.11
    yard
    -0.11
    ãģ£ãģ
    -0.10
    جز
    -0.10
    peed
    -0.09
    -0.09
    çħĮ
    -0.09
    ç¢Ľ
    -0.09
    strap
    -0.09
    ../
    -0.09
    POSITIVE LOGITS
    lah
    0.13
    ively
    0.13
    ine
    0.11
    ienne
    0.11
    nya
    0.10
    æºIJæºIJ
    0.10
    nal
    0.10
    ¡
    0.10
    ate
    0.10
    sing
    0.10
    Activations Density 0.013%

    No Known Activations