© 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. 32229
    Prev
    Next
    INDEX
    Explanations

    phrases with help

    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
    å§Ŀ
    -0.09
    _CMP
    -0.09
     Bergen
    -0.09
    诱导
    -0.09
     mac
    -0.09
     Ale
    -0.08
    讯
    -0.08
    å°Ĭéĩį
    -0.08
    ronym
    -0.08
    æ®Ĭ
    -0.08
    POSITIVE LOGITS
    èĭĮ
    0.10
    注åĨĮ
    0.10
     коллекÑĤив
    0.09
    opo
    0.09
    ASIC
    0.09
    èķĥ
    0.09
    åŃļ
    0.09
     ÃŃch
    0.09
     Moore
    0.08
    -*-
    0.08
    Activations Density 0.080%

    No Known Activations