© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3381
    Prev
    Next
    INDEX
    Explanations

    support and funding

    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
    GLOBALS
    -0.10
    çīµæĮĤ
    -0.09
    æ¯ıæ¯ı
    -0.08
    强åĪ¶
    -0.08
    å¯Ħ
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.08
    ONGLONG
    -0.08
    æĦŁè§¦
    -0.08
    è¯Ŀé¢ĺ
    -0.08
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.13
    æĢ¥éľĢ
    0.11
    符åIJĪ
    0.11
     eligible
    0.10
    éĩ
    0.10
    æıŃ
    0.10
    imeo
    0.09
    éľ¹
    0.09
    å·©
    0.09
    ä¸įåħ·å¤ĩ
    0.09
    Activations Density 0.084%

    No Known Activations