© 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. 7476
    Prev
    Next
    INDEX
    Explanations

    compound bows, sparkling wines, analog reception, used car

    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
    /license
    -0.10
    /operator
    -0.09
    çĺŁ
    -0.09
    æĦł
    -0.08
    ìŀ¥
    -0.08
    hopefully
    -0.08
    æ¸ħæ¾Ī
    -0.08
    edImage
    -0.08
    /tool
    -0.08
    大çļĦ
    -0.08
    POSITIVE LOGITS
    -ish
    0.10
    ä¸İåIJ¦
    0.10
    -leaning
    0.10
    -only
    0.09
    人士
    0.09
    æĥħåĨµä¸ĭ
    0.09
    æĪIJ份
    0.08
    ouncill
    0.08
    å½ĵä»ĸ
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    Activations Density 0.597%

    No Known Activations