© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63743
    Prev
    Next
    INDEX
    Explanations

    safety and security warnings

    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
     Cooler
    -0.09
    ä»»æľŁ
    -0.08
    åĥµ
    -0.08
     Transparent
    -0.08
    ansi
    -0.08
    anye
    -0.08
     Äijáp
    -0.08
    巨人
    -0.07
    èļķ
    -0.07
    ç©Ĺ
    -0.07
    POSITIVE LOGITS
    å®īåħ¨
    0.30
    çļĦå®īåħ¨
    0.29
     safety
    0.28
    å®īåħ¨æĢ§
    0.27
    åį±éĻ©
    0.27
    å®īåħ¨éļIJæĤ£
    0.26
    Safety
    0.26
     Safety
    0.26
    å®īåħ¨ç®¡çIJĨ
    0.24
    å®īåħ¨çĶŁäº§
    0.23
    Activations Density 0.160%

    No Known Activations