© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    prolific writer, aliens, production, experience

    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
    æľīæīĢ
    -0.10
    èħ¥
    -0.09
    侥幸
    -0.09
    ä¸ĩ个
    -0.09
    orf
    -0.08
    oker
    -0.08
    å¼¼
    -0.08
    /cop
    -0.08
    Georgia
    -0.08
    elper
    -0.08
    POSITIVE LOGITS
    èµľ
    0.11
    ond
    0.10
    ally
    0.10
    mu
    0.09
    anes
    0.09
    ../../../
    0.09
     во
    0.09
     impro
    0.09
    -bodied
    0.09
    ä¸Ģåı£æ°Ķ
    0.09
    Activations Density 0.008%

    No Known Activations