© 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. 38453
    Prev
    Next
    INDEX
    Explanations

    measure or measuring

    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
    ene
    -0.10
    åįĵè¶Ĭ
    -0.10
    atter
    -0.10
    assa
    -0.09
    unfold
    -0.09
    è°IJ
    -0.09
    ène
    -0.09
    atar
    -0.08
    hire
    -0.08
    ìĥģìĿĦ
    -0.08
    POSITIVE LOGITS
    è¡¡éĩı
    0.10
    ä¸Ī
    0.09
    .measure
    0.09
     Measure
    0.09
     thai
    0.09
    æĹĭ
    0.08
     measuring
    0.08
    UREMENT
    0.08
     measure
    0.08
    è¿ĻçĤ¹
    0.08
    Activations Density 0.155%

    No Known Activations