© 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. 19184
    Prev
    Next
    INDEX
    Explanations

    producer or produced

    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
    å®ľ
    -0.09
    æĢĢæĬ±
    -0.09
    Expose
    -0.09
    fällig
    -0.09
    affles
    -0.09
    çªĥ
    -0.09
    åľ¨è·¯ä¸Ĭ
    -0.08
    çĻ½é©¬
    -0.08
    çĸ¾
    -0.08
    configs
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.11
    ä¸Ģæīĭ
    0.10
    åģı
    0.09
    æĺ¾çĦ¶
    0.09
    æĺ¾
    0.09
    顯
    0.09
    æģ°
    0.09
    è¯¥æł¡
    0.09
    è¢ĸ
    0.09
    ç¼ĸåī§
    0.08
    Activations Density 0.056%

    No Known Activations