© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37794
    Prev
    Next
    INDEX
    Explanations

    moon

    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
    åĦ¿
    -0.10
    寡
    -0.09
    æ¯į
    -0.09
    ods
    -0.08
    éĢļãĤĬ
    -0.08
    ers
    -0.08
    çł´
    -0.08
    urdy
    -0.08
    æīĺ
    -0.08
    å²Ĺ
    -0.08
    POSITIVE LOGITS
    æĹ·
    0.09
    Legendary
    0.08
    èĬ±
    0.08
    âŀ¡
    0.08
    é£İæīĩ
    0.08
    fab
    0.08
     fan
    0.08
    èĤ¥
    0.08
    bject
    0.08
    åĨħå¿ĥ
    0.08
    Activations Density 0.002%

    No Known Activations