© 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. 52495
    Prev
    Next
    INDEX
    Explanations

    task force

    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
    archy
    -0.10
    ä¸ŀ
    -0.09
    illage
    -0.09
    icom
    -0.09
    laughter
    -0.09
    æŶæĬ¥
    -0.09
    thood
    -0.09
    /GL
    -0.09
    è¿Ļä¹Łæĺ¯
    -0.09
    éŃij
    -0.08
    POSITIVE LOGITS
    ç»Ħéķ¿
    0.10
    åīįç½®
    0.10
    éķ¿å¯¿
    0.09
    解åĨ³
    0.08
    岿
    0.08
    ðŁı»
    0.08
    æĭĨè¿ģ
    0.08
    åĴª
    0.08
    OSC
    0.08
     Gutenberg
    0.08
    Activations Density 0.021%

    No Known Activations