© 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. 37964
    Prev
    Next
    INDEX
    Explanations

    brand new

    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
    uner
    -0.09
    istik
    -0.09
    çĴĩ
    -0.09
    è¸Į
    -0.09
    interopRequireDefault
    -0.08
    ì¹ł
    -0.08
    ATER
    -0.08
     Rosen
    -0.08
    åIJģ
    -0.08
    çĿ¨
    -0.08
    POSITIVE LOGITS
    è°Ĺ
    0.08
    åIJĪ并
    0.08
    æĸĭ
    0.07
    itar
    0.07
    å¾Ĺå¾Ī
    0.07
     SEM
    0.07
     Creek
    0.07
    æѤäºĭ
    0.07
     descendant
    0.07
    .mi
    0.07
    Activations Density 0.810%

    No Known Activations