© 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. 39336
    Prev
    Next
    INDEX
    Explanations

    picked without replacement from

    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
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    ç»Ī
    -0.09
    ../../../
    -0.09
    éĢł
    -0.09
    WithPath
    -0.09
    Wins
    -0.08
    -ground
    -0.08
    ç·
    -0.08
    PEC
    -0.08
    纬
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.10
    æĸŃ
    0.09
    åĪĨéĶĢ
    0.09
    è·Łä½ł
    0.09
    åĮ¿åIJį
    0.09
    eder
    0.08
    åħ¨çIJĥåĮĸ
    0.08
    ç§ĥ
    0.08
    æĸ·
    0.08
    anonymous
    0.08
    Activations Density 0.019%

    No Known Activations