© 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. 17898
    Prev
    Next
    INDEX
    Explanations

    dailies, dailymotion, Laila, Maulid

    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
    åĬ©çIJĨ
    -0.12
    ally
    -0.12
    æ¼ī
    -0.11
    主ä¹ī
    -0.10
    èĨĽ
    -0.10
    ½
    -0.09
    æģ¤
    -0.09
    ical
    -0.09
    ality
    -0.09
    DebugEnabled
    -0.09
    POSITIVE LOGITS
    eenth
    0.13
    fully
    0.10
    utation
    0.10
    lessly
    0.09
    lection
    0.09
    omat
    0.09
    iard
    0.09
    工夫
    0.09
    alysis
    0.09
    ffects
    0.09
    Activations Density 0.018%

    No Known Activations