© 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. 27276
    Prev
    Next
    INDEX
    Explanations

    time, separators, listings

    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
    èµı
    -0.09
     spared
    -0.09
    _HELPER
    -0.08
    utt
    -0.08
    noinspection
    -0.08
     ÑĢол
    -0.08
    .lo
    -0.08
    hab
    -0.08
    Č↵
    -0.08
    Berlin
    -0.08
    POSITIVE LOGITS
    -tm
    0.09
    encers
    0.08
    oders
    0.08
     unknown
    0.08
    çī
    0.08
    å¤ļå°ij
    0.08
    ystack
    0.08
    æ´ĭæ´ĭ
    0.08
    åķ¡
    0.08
    åıĸåĨ³äºİ
    0.08
    Activations Density 0.176%

    No Known Activations