© 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. 36279
    Prev
    Next
    INDEX
    Explanations

    violence and cruelty

    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
    ysi
    -0.10
    诽
    -0.10
    æݧ
    -0.09
    è§ļ
    -0.09
     Conspiracy
    -0.09
    èĢĥå¯Ł
    -0.09
    èĦĤ
    -0.09
    éªĵ
    -0.08
    æŀµ
    -0.08
    åľ®
    -0.08
    POSITIVE LOGITS
    è¡Ģèħ¥
    0.19
    æļ´åĬĽ
    0.17
    æĿĢæŃ»
    0.17
    æ®ĭå¿į
    0.16
    æĿĢ人
    0.15
    å±łæĿĢ
    0.15
    殺
    0.14
    æĿĢ
    0.14
     killing
    0.14
    æĿĢ害
    0.13
    Activations Density 0.134%

    No Known Activations