© 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. 27605
    Prev
    Next
    INDEX
    Explanations

    health risks

    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
    çĿ¦
    -0.10
    æĦŁåħ´è¶£
    -0.10
    åħ·æľīä¸Ģå®ļ
    -0.09
    çļĦåħ´è¶£
    -0.09
    æĪIJåĬŁçİĩ
    -0.08
     Lehr
    -0.08
    æĥij
    -0.08
    iny
    -0.08
    èĸĦå¼±
    -0.08
    æģ¤
    -0.08
    POSITIVE LOGITS
    åģ¥åº·
    0.13
    身ä½ĵåģ¥åº·
    0.10
    èĤ¥
    0.10
    _health
    0.10
     Health
    0.09
     health
    0.09
    åģ¥åº·ç®¡çIJĨ
    0.09
    ignum
    0.09
    çĶŁæ´»æĸ¹å¼ı
    0.09
    OSH
    0.09
    Activations Density 0.258%

    No Known Activations