© 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. 34459
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    ennie
    -0.10
    éĶ£
    -0.10
     Sized
    -0.09
    weit
    -0.09
     Fletcher
    -0.09
    åºķå±Ĥ
    -0.08
    顶
    -0.08
    åĨħåľ°
    -0.08
    _rg
    -0.08
    宽
    -0.08
    POSITIVE LOGITS
    çļĦ好
    0.10
    .biz
    0.09
    äºĨå¤ļå°ij
    0.09
     ÑģобÑģÑĤвенно
    0.08
    é©»
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    é¢ĦåĶ®
    0.08
    éĿŀ常çļĦ
    0.08
    æĢĤ
    0.08
    ç¾İ人
    0.08
    Activations Density 0.268%

    No Known Activations