© 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. 21930
    Prev
    Next
    INDEX
    Explanations

    SELinux or security policy

    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
    æį
    -0.10
    ä¼ī
    -0.09
    flux
    -0.09
     Geb
    -0.08
    ä¸ĵä¸ļæĬĢæľ¯
    -0.08
    æīĢå¾Ĺ
    -0.08
    åħ¬çĶ¨
    -0.08
    fusion
    -0.08
     flux
    -0.08
     obsess
    -0.08
    POSITIVE LOGITS
    åĵ²
    0.10
    .strict
    0.10
     STRICT
    0.10
    ucci
    0.09
    éļĶ离
    0.09
    ä¸¥æł¼çļĦ
    0.09
    åݳ
    0.09
    strict
    0.09
    _EXECUTE
    0.09
    ÑĢажа
    0.08
    Activations Density 0.253%

    No Known Activations