© 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. 2919
    Prev
    Next
    INDEX
    Explanations

    in mind

    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¨ģåĬĽ
    -0.09
    éĿłè°±
    -0.09
    顶
    -0.09
    elier
    -0.09
     Dillon
    -0.09
    åı©
    -0.09
    hift
    -0.09
    ping
    -0.09
    ugar
    -0.08
    åĸľ
    -0.08
    POSITIVE LOGITS
    åķ§
    0.09
     proverb
    0.09
    æľ¬æĬ¥
    0.09
    åİ»åģļ
    0.09
    obook
    0.08
    å¢Ļä¸Ĭ
    0.08
    æĹ®
    0.08
    æĹĦ
    0.08
     Burnett
    0.08
    rush
    0.08
    Activations Density 0.004%

    No Known Activations