© 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. 5251
    Prev
    Next
    INDEX
    Explanations

    vulnerability and risk

    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
    ä¸įä¸ĭ
    -0.11
    å¤ļåįĬ
    -0.10
    è°¦
    -0.10
    è¦ģ说
    -0.09
    foreground
    -0.09
     Bridges
    -0.09
    è¿Ħä»Ĭ
    -0.09
    addons
    -0.08
    壤
    -0.08
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    å¼±çĤ¹
    0.12
    èĸĦå¼±
    0.12
    æļ´éľ²
    0.12
    èĦĨå¼±
    0.11
    容æĺĵ
    0.11
     vulnerable
    0.10
    ä¸ºçĽ®æłĩ
    0.10
    æĺĵ
    0.10
    æ½ľåľ¨
    0.10
    æĺĵäºİ
    0.10
    Activations Density 0.091%

    No Known Activations