© 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. 21509
    Prev
    Next
    INDEX
    Explanations

    committing crimes or wrongdoing

    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
    éħ·
    -0.09
     Tic
    -0.08
    èĥ½åĬĽ
    -0.08
    欹
    -0.08
     ability
    -0.08
    满
    -0.08
     нап
    -0.08
    å°¸
    -0.08
    hest
    -0.07
    ego
    -0.07
    POSITIVE LOGITS
    byn
    0.10
     Äijẩy
    0.09
    æ·±å±Ĥ次
    0.09
    éĻĭ
    0.09
    第äºĮç§į
    0.09
    æĸ¡
    0.09
    两个维æĬ¤
    0.09
    主ä¸ļ
    0.09
    åħ¨ç¨ĭ
    0.09
    æ··æ·Ĩ
    0.09
    Activations Density 0.017%

    No Known Activations