© 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. 23364
    Prev
    Next
    INDEX
    Explanations

    title: followed by colon

    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
    alendar
    -0.10
    etic
    -0.09
    屯
    -0.09
    est
    -0.09
    shed
    -0.09
    ì°Į
    -0.09
    uke
    -0.09
    eur
    -0.09
    ritz
    -0.08
    enne
    -0.08
    POSITIVE LOGITS
    ÅŁim
    0.10
    led
    0.10
     лиÑĪÑĮ
    0.10
    =title
    0.09
    éĨĽ
    0.09
     quo
    0.09
    WithPath
    0.09
    creen
    0.09
    èľ
    0.09
    ç½Ķ
    0.09
    Activations Density 0.055%

    No Known Activations