© 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. 63184
    Prev
    Next
    INDEX
    Explanations

    used to / used something

    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
    æŃ£å¦Ĥ
    -0.10
    oure
    -0.09
    _LVL
    -0.09
    puty
    -0.09
    pped
    -0.09
    pone
    -0.09
    emed
    -0.08
     Cult
    -0.08
    pping
    -0.08
    undo
    -0.08
    POSITIVE LOGITS
    efault
    0.10
    yna
    0.09
    ä¸įå½ĵ
    0.09
    åŁİå¢Ļ
    0.08
    ä¸įæŃ¢
    0.08
    åIJĮæľŁ
    0.08
    岬
    0.08
    ä¸įåĨį
    0.08
    é³ı
    0.08
    é»ĺå¥ij
    0.08
    Activations Density 0.075%

    No Known Activations