© 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. 2396
    Prev
    Next
    INDEX
    Explanations

    transform

    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
    avig
    -0.10
    åĿĬ
    -0.10
    è´Łè´£åIJĮå¿Ĺ
    -0.09
    ÑĮев
    -0.09
    عد
    -0.09
    å¾Īå¤ļæŶåĢĻ
    -0.09
     кон
    -0.09
    -handed
    -0.09
    amar
    -0.09
    trl
    -0.09
    POSITIVE LOGITS
    å·¥ä½ľä½ľé£İ
    0.11
    .Transform
    0.11
    (transform
    0.10
     Ñģобой
    0.10
    ä¹ĭæĹħ
    0.10
    ative
    0.10
    itin
    0.09
    -transform
    0.09
    ations
    0.09
    æĢ§çĸ¾çĹħ
    0.09
    Activations Density 0.039%

    No Known Activations