© 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. 923
    Prev
    Next
    INDEX
    Explanations

    invasion 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
    bum
    -0.09
     Blow
    -0.09
    isk
    -0.09
    è°Ģ
    -0.09
    rear
    -0.08
    riba
    -0.08
    秫
    -0.08
    leton
    -0.08
    åĨ³å®ļäºĨ
    -0.08
    åłĮ
    -0.08
    POSITIVE LOGITS
    å¤ĸæĿ¥
    0.12
    æī©æķ£
    0.11
    æľī害
    0.10
    移æ°ij
    0.10
    å¼ķåħ¥
    0.10
    æĢ¥
    0.10
    è·¨å¢ĥ
    0.09
     اÙĦأجÙĨبÙĬØ©
    0.09
     introduction
    0.09
    èĶĵ延
    0.09
    Activations Density 0.062%

    No Known Activations