© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10487
    Prev
    Next
    INDEX
    Explanations

    often used or available

    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
    稷
    -0.10
    ISTS
    -0.10
    ä½łçİ°åľ¨
    -0.10
    ä»ĸå¦Ī
    -0.09
    çĸĸ
    -0.09
    _remain
    -0.09
    Ķ
    -0.09
    å®īåºĨ
    -0.09
    æĽ´æľī
    -0.09
    ä¸įåIJ«
    -0.09
    POSITIVE LOGITS
    åĩ¡
    0.09
    åĩ¡æĺ¯
    0.09
     pair
    0.08
    lar
    0.08
    è§ı
    0.08
     Pair
    0.08
     Unified
    0.08
    pair
    0.08
    วย
    0.07
    æĨ¬
    0.07
    Activations Density 0.252%

    No Known Activations