© 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. 27994
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
    ction
    -0.11
    stairs
    -0.09
    åĮ»åѦéĻ¢
    -0.09
    owed
    -0.08
    iple
    -0.08
     лиÑĪÑĮ
    -0.08
    itive
    -0.08
     med
    -0.08
    inding
    -0.08
    ãĤĪãģĨãģ§
    -0.08
    POSITIVE LOGITS
    ically
    0.11
    ues
    0.11
    gon
    0.10
    icals
    0.10
    etics
    0.09
    ères
    0.09
    ical
    0.09
    ICAL
    0.09
    COPE
    0.09
    ently
    0.08
    Activations Density 0.011%

    No Known Activations