© 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. 53673
    Prev
    Next
    INDEX
    Explanations

    polynomial time complexity

    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
    ç§ĥ
    -0.10
    ç»
    -0.09
     bölüm
    -0.09
    æįIJèµł
    -0.09
     consec
    -0.09
    纯åĩĢ
    -0.09
     unst
    -0.08
    æĻĸ
    -0.08
    åıĪæľī
    -0.08
    plied
    -0.08
    POSITIVE LOGITS
    wed
    0.09
     bel
    0.09
    _deep
    0.09
    æħ¢
    0.09
    éĢĢ
    0.09
    æĤłéĹ²
    0.09
    ENUM
    0.08
    æīĭæĮĩ
    0.08
    ergarten
    0.08
    é»ij
    0.08
    Activations Density 0.123%

    No Known Activations