© 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. 6529
    Prev
    Next
    INDEX
    Explanations

    university press

    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
    åIJİèĢħ
    -0.09
    ationship
    -0.09
    itsu
    -0.09
    æݳ
    -0.08
     epis
    -0.08
    kbd
    -0.08
    gom
    -0.08
     CONTRIBUTORS
    -0.08
    tem
    -0.08
    vero
    -0.08
    POSITIVE LOGITS
     GANG
    0.10
    ä¸Ģ头
    0.09
    械
    0.09
    æ£
    0.09
    åĪĩåħ¥
    0.08
    æŁĦ
    0.08
    ä¸įå¿į
    0.08
    è´±
    0.08
    è¯ļæĦı
    0.08
    çĵł
    0.08
    Activations Density 0.007%

    No Known Activations