© 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. 48886
    Prev
    Next
    INDEX
    Explanations

    certification obtained

    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
    忽
    -0.10
    AppState
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    flake
    -0.09
    emic
    -0.08
    æIJŀ好
    -0.08
    å¼ĢæĿ¥
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    éĺ²æ±Ľ
    -0.08
     Pact
    -0.08
    POSITIVE LOGITS
    浪潮
    0.10
    ãģĸ
    0.09
    åIJİåĨį
    0.09
    çħ
    0.09
    urd
    0.09
    çĸ¼çĹĽ
    0.09
    大éŨ
    0.09
    ZE
    0.09
     Rev
    0.08
    åIJİçļĦ
    0.08
    Activations Density 0.043%

    No Known Activations