© 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. 54940
    Prev
    Next
    INDEX
    Explanations

    astrology, Astros, Astro, Castro

    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
    å°ıäºĭ
    -0.09
     sá»ķ
    -0.09
    èľĵ
    -0.09
    orses
    -0.09
    ìĹŃ
    -0.08
     spit
    -0.08
    èĨº
    -0.08
     Clarkson
    -0.08
    ç½ijéĢļ
    -0.08
    ucs
    -0.08
    POSITIVE LOGITS
    ships
    0.12
    ship
    0.12
    ium
    0.10
    shire
    0.10
    craft
    0.10
    gio
    0.09
    ãģĵãģ¨
    0.09
    ги
    0.09
    genic
    0.09
    gie
    0.09
    Activations Density 0.010%

    No Known Activations