© 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. 36079
    Prev
    Next
    INDEX
    Explanations

    eucalyptus, ulmo, oral, uchar

    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
    æĪĺ
    -0.09
    ç¦Ģ
    -0.09
    ä¸Ģ件
    -0.09
    åĪº
    -0.09
    èĭĵ
    -0.09
    piece
    -0.08
    reh
    -0.08
    éļį
    -0.08
     Piece
    -0.08
     ÑĦоÑĢмиÑĢов
    -0.08
    POSITIVE LOGITS
    uate
    0.10
    æħ·
    0.09
    oral
    0.09
    èĥĥåı£
    0.09
    åŀ¢
    0.09
    alia
    0.09
    -Sep
    0.09
    æĸĩæĺĮ
    0.09
    eat
    0.09
    uchar
    0.08
    Activations Density 0.004%

    No Known Activations