© 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. 30721
    Prev
    Next
    INDEX
    Explanations

    Council, Raider, Foundation

    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
    ender
    -0.09
    çĮ¿
    -0.08
    ä¿ĿéĻ©
    -0.08
    èĥľåĪ©
    -0.08
    æĬµæĬĹ
    -0.08
    åħļåĴĮæĶ¿åºľ
    -0.08
    .dy
    -0.08
    è¿Ļ份
    -0.08
    éĻªä½ł
    -0.08
    closed
    -0.08
    POSITIVE LOGITS
    å®ļä½į
    0.09
    adt
    0.09
    oup
    0.09
    isel
    0.09
    inia
    0.09
    å¿Ŀ
    0.08
    iosa
    0.08
    icas
    0.08
    .truth
    0.08
    çİĭèĢħ
    0.08
    Activations Density 0.030%

    No Known Activations