© 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. 50267
    Prev
    Next
    INDEX
    Explanations

    celestial bodies

    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
    è°İ
    -0.09
    acen
    -0.09
    uben
    -0.09
    æŁ¯
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.08
    Ĭ¶
    -0.08
    ç»Ĩ
    -0.08
    å¨ĺ
    -0.08
    /rec
    -0.08
    æ¼¾
    -0.08
    POSITIVE LOGITS
    usto
    0.10
    å¢ĥ
    0.10
    _RW
    0.09
    puter
    0.09
    ä¸įåħĭ
    0.09
    /org
    0.09
    بس
    0.09
    確ãģĭ
    0.09
    çļĦæ°Ķæģ¯
    0.09
    ä»ij
    0.08
    Activations Density 0.023%

    No Known Activations