© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7917
    Prev
    Next
    INDEX
    Explanations

    original author

    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
    è¿Ļå¥Ĺ
    -0.09
    è¿«ä¸įåıĬå¾ħ
    -0.09
    æIJĵ
    -0.09
    æľķ
    -0.09
    rms
    -0.08
    è¿ĻæĿ¡
    -0.08
    lain
    -0.08
    æıĨ
    -0.08
    åĢļ
    -0.08
    æģ£
    -0.08
    POSITIVE LOGITS
    3
    0.09
    èĥĮçĿĢ
    0.09
    7
    0.09
    1
    0.08
    5
    0.08
    6
    0.08
    8
    0.08
    æĶ¹
    0.08
    4
    0.08
    2
    0.08
    Activations Density 0.007%

    No Known Activations