© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20578
    Prev
    Next
    INDEX
    Explanations

    Liferay, LLC, Lei, Laf, lu

    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
    /Linux
    -0.11
    lund
    -0.10
     лиÑĪÑĮ
    -0.10
    çī¢
    -0.10
    ListOf
    -0.09
    uls
    -0.09
     lá»ĩnh
    -0.09
    OLON
    -0.09
    elves
    -0.09
    ilm
    -0.09
    POSITIVE LOGITS
    raries
    0.17
    RARY
    0.16
    itud
    0.14
    UNCH
    0.14
    undry
    0.14
    rador
    0.14
    rarian
    0.13
    auge
    0.13
     lẽ
    0.13
    AndServe
    0.13
    Activations Density 1.735%

    No Known Activations