© 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. 31648
    Prev
    Next
    INDEX
    Explanations

    renal calculi and salts

    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
    æł¹æľ¬
    -0.09
     вÑĭгод
    -0.09
    bish
    -0.08
    çļĦæľĢåIJİä¸Ģ
    -0.08
    alue
    -0.08
    mise
    -0.08
    å«
    -0.08
    åºĹéĿ¢
    -0.08
    sworth
    -0.08
    .controls
    -0.08
    POSITIVE LOGITS
    ç¢İçīĩ
    0.10
    izen
    0.10
    BREAK
    0.09
    碳éħ¸
    0.09
    çİ°åľ¨å¾Īå¤ļ
    0.09
    tic
    0.09
    breaking
    0.09
    éľ°
    0.09
    urus
    0.09
    æĹħéĢĶ
    0.09
    Activations Density 0.119%

    No Known Activations