© 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. 5114
    Prev
    Next
    INDEX
    Explanations

    stock tickers and company names

    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
    å¥Ĺè·¯
    -0.10
    éĿ¢çĽ®
    -0.09
    å°ıå§IJ
    -0.09
    åijĨ
    -0.09
    _visibility
    -0.09
    çŀ¥
    -0.09
    _abort
    -0.09
    延误
    -0.09
    åģ¶
    -0.09
    arters
    -0.08
    POSITIVE LOGITS
    wed
    0.09
    bolt
    0.08
    onus
    0.08
    Apis
    0.08
    cko
    0.08
    å±Ĥå±Ĥ
    0.08
    Ĥæķ°
    0.08
    èİ·å¾ĹæĽ´å¤ļ
    0.08
    (pipe
    0.08
    .exclude
    0.08
    Activations Density 0.039%

    No Known Activations