© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    actual results, interest, or value

    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
    ings
    -0.09
     полно
    -0.09
     normal
    -0.08
    ella
    -0.08
    pon
    -0.08
    nox
    -0.08
     strat
    -0.08
    park
    -0.07
     Birch
    -0.07
     mart
    -0.07
    POSITIVE LOGITS
    æĥħæ³ģ
    0.10
    çªĹå¤ĸ
    0.10
    åĩºåĩ»
    0.10
    gars
    0.10
    ercul
    0.10
    iros
    0.10
    ucus
    0.09
    .radians
    0.09
    åѤåĦ¿
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    Activations Density 0.015%

    No Known Activations