© 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. 48542
    Prev
    Next
    INDEX
    Explanations

    copy, paste, or copyright

    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
    ÅĽli
    -0.10
    涯
    -0.09
    èģĺçĶ¨
    -0.09
    Ø´Ùĥ
    -0.09
    awei
    -0.09
    åĵªæĢķæĺ¯
    -0.09
    æĢĿ
    -0.09
    æ¦Ĥ
    -0.08
    æĹħ游
    -0.08
    秣
    -0.08
    POSITIVE LOGITS
    .deepcopy
    0.15
    .copy
    0.12
    .Copy
    0.12
    èªĬ
    0.10
     paste
    0.10
    å¤įåĪ¶
    0.10
     copies
    0.09
    æĭ·
    0.09
    Paste
    0.09
     copy
    0.09
    Activations Density 0.099%

    No Known Activations