© 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. 31032
    Prev
    Next
    INDEX
    Explanations

    Blair, flair, flat

    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
    สรร
    -0.11
    eko
    -0.11
    ëģĶ
    -0.11
    vida
    -0.10
    ober
    -0.10
    berger
    -0.09
    itive
    -0.09
    ario
    -0.09
    LOT
    -0.09
    ally
    -0.09
    POSITIVE LOGITS
    ÑĢ
    0.11
    ships
    0.10
    ulent
    0.09
    lining
    0.09
    centage
    0.09
    æŃ¤äºº
    0.09
    æĭ¢
    0.09
     JNIEnv
    0.08
    ä¸ı
    0.08
    mps
    0.08
    Activations Density 0.002%

    No Known Activations