© 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. 54189
    Prev
    Next
    INDEX
    Explanations

    stealthy movement

    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
    æĬĹ
    -0.10
    åĭī
    -0.10
     Gros
    -0.09
    å½»
    -0.09
    壮
    -0.09
    empor
    -0.09
    æĭīçĿĢ
    -0.08
    ramento
    -0.08
    æµİ
    -0.08
    æĬĬæĮģ
    -0.08
    POSITIVE LOGITS
    æīĵæĭĽåij¼
    0.10
    å¼ĢèįĴ
    0.09
    èѦ
    0.09
    ä¾¦å¯Ł
    0.09
    æĤĦ
    0.09
    路人
    0.09
    ä¾¦æŁ¥
    0.09
     пÑĢедмеÑĤ
    0.09
    çļĦèĦļæŃ¥
    0.09
    å¥ĸåѦéĩij
    0.09
    Activations Density 0.046%

    No Known Activations