© 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. 32142
    Prev
    Next
    INDEX
    Explanations

    pont / ponte beginnings

    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
    igi
    -0.10
    tron
    -0.09
    pace
    -0.09
    hood
    -0.09
    istically
    -0.09
    å®ĺæĸ¹å¾®ä¿¡
    -0.09
    åIJĦçķĮ
    -0.08
    joint
    -0.08
    teenth
    -0.08
    æľīæĦı
    -0.08
    POSITIVE LOGITS
    eurs
    0.12
    ¼
    0.10
    azzi
    0.10
    ythe
    0.10
    иÑĪÑĮ
    0.09
    ering
    0.09
    eur
    0.09
    ibraries
    0.09
    -third
    0.09
    uação
    0.09
    Activations Density 0.010%

    No Known Activations