© 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. 4495
    Prev
    Next
    INDEX
    Explanations

    government

    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
    .tim
    -0.09
    conf
    -0.08
    DET
    -0.08
    adesh
    -0.08
    åīįåĪĹ
    -0.08
    åħ¨åŁŁ
    -0.08
    èģĶåIJĪåĽ½
    -0.08
     tand
    -0.08
    uffy
    -0.08
    Gb
    -0.08
    POSITIVE LOGITS
    代åĬŀ
    0.11
    人çĶŁçļĦ
    0.09
    gov
    0.09
    ä¿ĿçķĻ
    0.09
    ktor
    0.09
    çļĦéĩį大
    0.09
    å¸Ķ
    0.08
     fried
    0.08
    éĢĤ度
    0.08
    OURS
    0.08
    Activations Density 0.030%

    No Known Activations