© 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. 62986
    Prev
    Next
    INDEX
    Explanations

    names ending in rix, ton, ana, acea

    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
    æģģ
    -0.09
    eree
    -0.09
    诡
    -0.08
    itel
    -0.08
    á»ģn
    -0.08
    IPH
    -0.08
    å·§
    -0.08
    رش
    -0.08
    busters
    -0.08
     kitabı
    -0.08
    POSITIVE LOGITS
    èĪĦ
    0.10
    vä
    0.09
    éģĹå¿ĺ
    0.09
    è¿Ļæīįæĺ¯
    0.09
    UME
    0.09
    çľĭä¸Ģçľĭ
    0.09
    ican
    0.09
    ç©°
    0.09
    hma
    0.09
    lica
    0.09
    Activations Density 0.002%

    No Known Activations