© 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. 31409
    Prev
    Next
    INDEX
    Explanations

    world war

    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
    vik
    -0.10
    enerated
    -0.09
    ẻ
    -0.09
    éĿ¢èī²
    -0.09
     Noel
    -0.09
    è¾Ī
    -0.09
    ä½ĵåĨħ
    -0.09
    身é«Ķ
    -0.09
    åĩºåľº
    -0.08
    ä¸ĸçķĮç»ıæµİ
    -0.08
    POSITIVE LOGITS
    ful
    0.11
    FUL
    0.10
    lish
    0.09
    melon
    0.09
    åĿĢ
    0.09
    еÑĢÑĮ
    0.09
    eur
    0.09
    aml
    0.09
    æIJŃ
    0.09
    mel
    0.08
    Activations Density 0.019%

    No Known Activations