© 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. 57921
    Prev
    Next
    INDEX
    Explanations

    government legislation authorization vote

    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
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    åİ¿éķ¿
    -0.09
    æīĵæ³ķ
    -0.09
    åĥı个
    -0.09
    å¨ĺ
    -0.08
    åİ¿æĶ¿åºľ
    -0.08
    åĴı
    -0.08
    åĻĹ
    -0.08
    .policy
    -0.08
     Cav
    -0.08
    POSITIVE LOGITS
    饮çĶ¨
    0.09
    .Touch
    0.09
     ---------------------------------------------------------------------------↵
    0.09
    饮水
    0.09
    èªī
    0.08
    ihn
    0.08
    榷
    0.08
     châu
    0.08
    è¤
    0.08
    å¼ķçĶ¨
    0.08
    Activations Density 0.075%

    No Known Activations