© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    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
     yaÅŁam
    -0.08
    èIJ¥åħ»
    -0.08
    nea
    -0.08
    çĦĺ
    -0.08
     Estates
    -0.08
    æīĺè¿IJ
    -0.08
    å®īå®ļ
    -0.08
    arme
    -0.08
    FromArray
    -0.08
    thumbs
    -0.08
    POSITIVE LOGITS
    èŁ¾
    0.09
    pink
    0.09
    edin
    0.09
    ç¨ĭ度
    0.09
    æĸĹ
    0.09
    çIJIJ
    0.09
    èĿĩ
    0.08
    è°¯
    0.08
    çĵ¶åŃIJ
    0.08
    澡
    0.08
    Activations Density 0.048%

    No Known Activations