© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    or otherwise

    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
     Ips
    -0.11
    kie
    -0.10
    TestClass
    -0.09
    çŀ§
    -0.09
    urat
    -0.08
    getApplication
    -0.08
    ç»Ī
    -0.08
    castle
    -0.08
    éķIJ
    -0.08
    æIJŀ
    -0.08
    POSITIVE LOGITS
     otherwise
    0.18
    åIJ¦åĪĻ
    0.17
    otherwise
    0.16
    ä¸įçĦ¶
    0.16
    ä¹Łæĺ¯å¦ĤæѤ
    0.15
     OTHERWISE
    0.14
     Otherwise
    0.13
    Otherwise
    0.13
    åIJ¦åīĩ
    0.13
    åıįä¹ĭ
    0.13
    Activations Density 0.111%

    No Known Activations