© 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. 23517
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    ä¸įèµ·
    -0.10
    ä¼ĹæīĢåij¨çŁ¥
    -0.10
     ``(
    -0.09
    ä¸įä½ı
    -0.09
    ewise
    -0.09
    خب
    -0.08
    使人
    -0.08
    urst
    -0.08
    uum
    -0.08
    ToWorld
    -0.08
    POSITIVE LOGITS
    çĶŁæĪIJ
    0.17
     generated
    0.16
     èĩªåĬ¨çĶŁæĪIJ
    0.14
     generate
    0.13
     generation
    0.13
    .generate
    0.13
    generated
    0.13
    generate
    0.13
    -generated
    0.13
    åĩºæĿ¥çļĦ
    0.12
    Activations Density 0.287%

    No Known Activations