© 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. 17583
    Prev
    Next
    INDEX
    Explanations

    although, that, if, most, been

    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
    åı¯æĥ³èĢĮçŁ¥
    -0.10
    ä¸įåĪ©äºİ
    -0.09
     unfortunately
    -0.09
    argout
    -0.09
    otron
    -0.09
    gün
    -0.08
    èĢĢ
    -0.08
    缮çļĦåľ°
    -0.08
    åħ¥
    -0.08
    ONGL
    -0.08
    POSITIVE LOGITS
    并ä¸įä¼ļ
    0.17
    ä¸įèĩ³äºİ
    0.15
    æĹłåħ³
    0.15
    ä¸įå½±åĵį
    0.14
     innoc
    0.13
    å°±ä¸įä¼ļ
    0.13
    ä¸įä¼ļ
    0.12
     harmless
    0.12
     insign
    0.11
     benign
    0.11
    Activations Density 0.303%

    No Known Activations