© 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. 55390
    Prev
    Next
    INDEX
    Explanations

    back and forth

    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
    è¡ĮåĬ¨è®¡åĪĴ
    -0.11
    Ïİ
    -0.09
    plet
    -0.09
    oplast
    -0.09
    sembly
    -0.09
     wrink
    -0.09
    éªı
    -0.09
    пл
    -0.08
    uled
    -0.08
    fluid
    -0.08
    POSITIVE LOGITS
    媳
    0.09
    inea
    0.08
     sexes
    0.08
    ëĦ·
    0.08
    abouts
    0.08
    s
    0.08
    åŀł
    0.08
    sWith
    0.08
    essel
    0.08
    æģ¨
    0.08
    Activations Density 0.009%

    No Known Activations