© 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. 55790
    Prev
    Next
    INDEX
    Explanations

    dockerfile commands

    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
    istributor
    -0.09
    æ»´æ»´
    -0.09
    azers
    -0.09
    åħ¨å±Ģ
    -0.09
    讼
    -0.09
    æ¥Ķ
    -0.09
     dripping
    -0.08
    ìĬ¬
    -0.08
    èįī
    -0.08
    æĽ²æĬĺ
    -0.08
    POSITIVE LOGITS
    éķľ
    0.09
    çļ®èĤ¤çĹħ
    0.09
     Tin
    0.09
    被çĽĹ
    0.09
    é£İåı£
    0.09
    éĨī
    0.09
    åĨ»ç»ĵ
    0.09
    åIJĨ
    0.08
    ä¸įæĽ¾
    0.08
    èĪ¸
    0.08
    Activations Density 0.174%

    No Known Activations