© 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. 35305
    Prev
    Next
    INDEX
    Explanations

    security and privacy regulation

    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
    éĩĮç¨ĭ
    -0.10
    äºĽä»Ģä¹Ī
    -0.09
    æīĵæ³ķ
    -0.09
    娣
    -0.09
    èıı
    -0.09
    å¾Ī满æĦı
    -0.09
    çµ®
    -0.09
    vice
    -0.09
    ieces
    -0.09
     CDDL
    -0.09
    POSITIVE LOGITS
    çĽĹçªĥ
    0.09
    ä¿Ŀå®ī
    0.08
    strup
    0.08
     bore
    0.08
    hung
    0.08
    社
    0.08
     burg
    0.08
    8
    0.07
    ICON
    0.07
    æ°ij主
    0.07
    Activations Density 0.016%

    No Known Activations