© 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. 30014
    Prev
    Next
    INDEX
    Explanations

    in charge of

    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
    æĪIJ份
    -0.10
    _esc
    -0.10
    åħħ足çļĦ
    -0.09
    ież
    -0.09
    åħĦå¼Ł
    -0.09
    åĪĨ离
    -0.09
    对ä»ĸ们
    -0.09
    Ñīин
    -0.09
    éĤĢ
    -0.09
    çļĦçIJĨ解
    -0.09
    POSITIVE LOGITS
    è´Łè´£
    0.26
     responsible
    0.21
    è²łè²¬
    0.20
     responsável
    0.16
     responsibility
    0.15
     Responsible
    0.15
    è´Łè´£ä»»
    0.14
    è´Łè´£äºº
    0.14
    ponsible
    0.14
    主管
    0.13
    Activations Density 0.067%

    No Known Activations