© 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. 17755
    Prev
    Next
    INDEX
    Explanations

    differences between/in

    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
    itude
    -0.10
    ural
    -0.09
    iek
    -0.09
    aque
    -0.09
    æĦŁ
    -0.09
    auge
    -0.09
    umber
    -0.09
     Andres
    -0.09
    isphere
    -0.08
    èł¹
    -0.08
    POSITIVE LOGITS
    ERENCE
    0.10
    rence
    0.10
    InParameter
    0.09
    太大
    0.09
    æ±Łæ·®
    0.09
    _between
    0.09
    iculty
    0.09
    ently
    0.08
     Toast
    0.08
    conti
    0.08
    Activations Density 0.057%

    No Known Activations