© 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. 21991
    Prev
    Next
    INDEX
    Explanations

    government, army, state, police

    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
    åĩı
    -0.09
     ASA
    -0.09
    åħīèį£
    -0.09
     labs
    -0.09
    举
    -0.08
     petty
    -0.08
    åī¯æľ¬
    -0.08
    æĦŁæŁĵ
    -0.08
    \↵
    -0.08
    ä¸įå®ī
    -0.08
    POSITIVE LOGITS
    æīĵåİĭ
    0.13
    å±łæĿĢ
    0.12
    åİĭåĪ¶
    0.12
    对ä»ĺ
    0.11
    åĩºåĬ¨
    0.11
    éķĩ
    0.10
    è¡Ģèħ¥
    0.10
     crackdown
    0.10
    èģļéĽĨ
    0.10
    çŀĢ
    0.10
    Activations Density 0.056%

    No Known Activations