© 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. 57271
    Prev
    Next
    INDEX
    Explanations

    and or to

    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
    lder
    -0.11
    çľĭä½ł
    -0.10
    anium
    -0.10
    -drive
    -0.09
    egan
    -0.09
    	TokenName
    -0.09
    .drive
    -0.09
    çIJĨ论ä¸Ĭ
    -0.09
    аннÑĭ
    -0.09
     nhiá»ĩt
    -0.09
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.18
    ä¸Ĭä¸ĭ
    0.16
    åīįåIJİ
    0.15
    -and
    0.14
    é«ĺä½İ
    0.13
    åĩºåħ¥
    0.13
    InOut
    0.13
    è¿Ľåĩº
    0.12
    æĿ¥åĽŀ
    0.11
     lẫn
    0.11
    Activations Density 0.178%

    No Known Activations