© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    peel/peeled/peeling

    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
    è¹ĭ
    -0.10
    åIJ¸
    -0.10
    presso
    -0.09
    erving
    -0.09
    æīĺ管
    -0.09
    moz
    -0.09
    å·¡
    -0.09
    stag
    -0.08
    iesta
    -0.08
     Äijá»īnh
    -0.08
    POSITIVE LOGITS
    åŁł
    0.09
    -pe
    0.09
    åīĬ
    0.09
    è±³
    0.08
    ape
    0.08
    лав
    0.08
     separ
    0.08
    IDX
    0.08
    ENTS
    0.08
    è¤ļ
    0.08
    Activations Density 0.012%

    No Known Activations