© 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. 4941
    Prev
    Next
    INDEX
    Explanations

    dangerous and formidable situations

    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
    éģŃ
    -0.10
    éģŃéģĩ
    -0.10
    åģĮ
    -0.09
    ç²¾åĵģ
    -0.09
    æµ®
    -0.09
    éģŃåĪ°
    -0.09
    uced
    -0.08
    åľ¨è¿ĻéĩĮ
    -0.08
    ç£ķ
    -0.08
    åºĨ幸
    -0.08
    POSITIVE LOGITS
     capable
    0.12
     powerful
    0.11
     potent
    0.11
     formidable
    0.11
    强大çļĦ
    0.11
    æĦıåĽ¾
    0.11
    强大
    0.11
    çļĦ强大
    0.11
    åı¯æĢķ
    0.11
     dangerous
    0.10
    Activations Density 0.076%

    No Known Activations