© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21343
    Prev
    Next
    INDEX
    Explanations

    Luksik Krawchuk Epie

    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
    вен
    -0.09
    erator
    -0.09
    ä¸Ģæľ¬ä¹¦
    -0.08
    ois
    -0.08
    ä»ĺ
    -0.08
     волн
    -0.08
    袱
    -0.08
    cé
    -0.08
    æ³ķå®ļ
    -0.08
    Ê·
    -0.08
    POSITIVE LOGITS
    ry
    0.10
    stakes
    0.10
    ght
    0.10
    pane
    0.09
    ocity
    0.09
    ight
    0.09
    æķĻåŃ¦è´¨éĩı
    0.08
    ment
    0.08
    好转
    0.08
    à¹īาà¸ĩ
    0.08
    Activations Density 0.229%

    No Known Activations