© 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. 18114
    Prev
    Next
    INDEX
    Explanations

    portfolio

    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
    .pet
    -0.09
    æĶ¯çº¿
    -0.09
    -guide
    -0.09
    溯æºIJ
    -0.08
    姿
    -0.08
    å¸Ń
    -0.08
    _physical
    -0.08
    导è´Ń
    -0.08
    .gstatic
    -0.08
    管çIJĨåijĺ
    -0.08
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.16
    à¸ľà¸¥à¸ĩาà¸Ļ
    0.13
    portfolio
    0.12
    ä¸ļ绩
    0.11
     portfolio
    0.11
    åªĴä½ĵæĬ¥éģĵ
    0.11
    åħīå½±
    0.11
    çļĦä½ľåĵģ
    0.11
    Portfolio
    0.11
     Portfolio
    0.11
    Activations Density 0.116%

    No Known Activations