© 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. 33966
    Prev
    Next
    INDEX
    Explanations

    year inupdatevirussalinity

    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
    åīįè¿°
    -0.08
    sWith
    -0.08
    inated
    -0.08
    ç¨ļ
    -0.08
    æĥ³åĪ°äºĨ
    -0.08
    èĦijåŃIJéĩĮ
    -0.07
     ãĢĮ
    -0.07
    actively
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    ÑĤиÑĢов
    -0.07
    POSITIVE LOGITS
    orne
    0.10
    æĥĬ人
    0.10
    lane
    0.10
    erre
    0.09
     Brill
    0.09
    é¬ĵ
    0.09
    æĹłåģ¿
    0.09
    Strip
    0.09
    æį·
    0.09
    å·²ä¹ħ
    0.09
    Activations Density 0.108%

    No Known Activations