© 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. 56683
    Prev
    Next
    INDEX
    Explanations

    USDA or DC abbreviations

    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
     Ñģобой
    -0.10
    ä¼ĹæīĢ
    -0.09
    åľ°ä¸Ńæµ·
    -0.09
    mas
    -0.09
    quent
    -0.08
    atern
    -0.08
    toa
    -0.08
    ulary
    -0.08
    vant
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    POSITIVE LOGITS
    ฯ
    0.11
    ени
    0.10
    ä¿®æŃ£
    0.10
    -best
    0.09
    yne
    0.09
    ache
    0.09
    _rng
    0.09
    说æĺİ书
    0.09
    ÑĢаÐ
    0.08
    _lite
    0.08
    Activations Density 0.003%

    No Known Activations