© 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. 54111
    Prev
    Next
    INDEX
    Explanations

    creative output or solutions

    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¸Ģ件
    -0.08
    åIJį家
    -0.08
    Inline
    -0.08
    asca
    -0.08
     Talk
    -0.08
    çļĦäºĭå®ŀ
    -0.08
    羣çIJĨ
    -0.08
    itar
    -0.08
    ä¸ĵä¸ļåĮĸ
    -0.08
     ment
    -0.08
    POSITIVE LOGITS
    åĪĽæĦı
    0.15
    åĪĽéĢłæĢ§
    0.12
    æĥ³è±¡åĬĽ
    0.12
    å±Ĥåĩºä¸įç©·
    0.11
    åĪĽéĢłåĬĽ
    0.11
    åıijè§ī
    0.10
    æĢĿè·¯
    0.10
    _exports
    0.10
    çİ©æ³ķ
    0.10
    æĥ³æ³ķ
    0.10
    Activations Density 0.041%

    No Known Activations