© 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. 54351
    Prev
    Next
    INDEX
    Explanations

    meso-

    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
    ÑĢед
    -0.09
    姿æĢģ
    -0.08
    è§ģ解
    -0.08
    ursal
    -0.08
    eln
    -0.08
    thing
    -0.08
    uppe
    -0.08
    adius
    -0.08
    toa
    -0.08
    DOMNode
    -0.08
    POSITIVE LOGITS
    ioned
    0.12
    amble
    0.11
    urement
    0.11
    è´»
    0.10
    æŃ£åľ¨è¿Ľè¡Į
    0.09
     Zuk
    0.09
    -vous
    0.09
    ÙĪرÙĬ
    0.09
    主ä¹ī
    0.08
    ä¸įåIJĮç±»åŀĭ
    0.08
    Activations Density 0.029%

    No Known Activations