© 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. 30447
    Prev
    Next
    INDEX
    Explanations

    ple- prefix or words starting with ple

    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
    upo
    -0.09
    noon
    -0.09
    ×Ļ×ķת
    -0.08
    icity
    -0.08
    ooter
    -0.08
    ²
    -0.08
    él
    -0.08
    ucer
    -0.08
     же
    -0.08
    shire
    -0.08
    POSITIVE LOGITS
    fully
    0.14
    ãģĹãģı
    0.10
    antic
    0.10
    tern
    0.10
     гаÑĢ
    0.09
    eso
    0.09
    ìį¨
    0.09
    wort
    0.09
    enting
    0.09
    antry
    0.09
    Activations Density 0.021%

    No Known Activations