© 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. 4154
    Prev
    Next
    INDEX
    Explanations

    prank calls and April Fool's

    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
    uem
    -0.09
     Cliff
    -0.09
    -wow
    -0.09
    Ĩ
    -0.08
    ä¸įåĩº
    -0.08
     vag
    -0.08
    åĿł
    -0.08
    ÙĪع
    -0.08
    Lou
    -0.08
    -san
    -0.08
    POSITIVE LOGITS
    sters
    0.11
    alytics
    0.10
    ../../../
    0.10
    ishly
    0.10
    거리
    0.09
    声åĵį
    0.09
    ish
    0.09
    fully
    0.08
    eson
    0.08
    MASTER
    0.08
    Activations Density 0.004%

    No Known Activations