© 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. 48397
    Prev
    Next
    INDEX
    Explanations

    Builder. Builder

    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
    ä¸Ģç«Ļ
    -0.09
    ainter
    -0.08
     Barn
    -0.08
    ä¸Ģå¿ĥ
    -0.08
    tractor
    -0.08
     USB
    -0.08
    liner
    -0.08
    峪
    -0.08
    æĭ¥æĬ¤
    -0.08
    PullParser
    -0.07
    POSITIVE LOGITS
    ä½ıäºĨ
    0.10
    æĬ¬èµ·
    0.09
    åģļäºĨ
    0.08
    elong
    0.08
    赶ä¸Ĭ
    0.08
    侯
    0.08
    hack
    0.08
    igrated
    0.08
    çľĭå®Į
    0.08
    对该
    0.08
    Activations Density 0.869%

    No Known Activations