© 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. 21686
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    aland
    -0.09
    .CG
    -0.09
    èĸ®
    -0.08
    :NO
    -0.08
    ละà¸Ħร
    -0.08
    è¢ĸ
    -0.08
    ego
    -0.08
    auen
    -0.08
    lang
    -0.08
     PB
    -0.08
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.10
    éļ¾æĢª
    0.10
    ä¸įåıĺ
    0.09
    çķĻåľ¨
    0.09
    æ¸İ
    0.09
    说åĩºæĿ¥
    0.09
    ä¹ĸä¹ĸ
    0.09
    ìĹŃ
    0.09
    çĩ¥
    0.08
    ä¿Ŀå®Ī
    0.08
    Activations Density 0.013%

    No Known Activations