© 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. 58473
    Prev
    Next
    INDEX
    Explanations

    median statistics

    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
    eut
    -0.08
    rou
    -0.08
    è¿ĽæĿ¥
    -0.08
    iller
    -0.08
    drv
    -0.08
     dope
    -0.08
    erview
    -0.07
    åѦåĪ°
    -0.07
    меÑĢ
    -0.07
    è¿ĽäºĨ
    -0.07
    POSITIVE LOGITS
    stral
    0.11
    mium
    0.10
    大èĴľ
    0.10
    å¹´é¾Ħ
    0.09
    ataire
    0.09
    ÙĦج
    0.09
    hari
    0.09
    uting
    0.09
    ployment
    0.09
    afil
    0.09
    Activations Density 0.020%

    No Known Activations