© 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. 18194
    Prev
    Next
    INDEX
    Explanations

    frederick followed by a name

    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
    诣
    -0.10
    ç´¯äºĨ
    -0.10
    culate
    -0.09
    ÑĢÑĥб
    -0.09
    uth
    -0.09
    æĬĢèĥ½åŁ¹è®Ń
    -0.09
    åĪ©åĻ¨
    -0.08
    mates
    -0.08
    iper
    -0.08
    ored
    -0.08
    POSITIVE LOGITS
    angelo
    0.11
    ../../../
    0.11
    son
    0.11
    à¹Į
    0.10
    sons
    0.10
    fone
    0.09
    shire
    0.09
    ìĬ¨
    0.09
    emos
    0.09
    ksen
    0.08
    Activations Density 0.019%

    No Known Activations