© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8617
    Prev
    Next
    INDEX
    Explanations

    court cases, legal citations, and mathematical expressions

    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
    游æĪıä¸Ń
    -0.10
    ãĥ¼ãĥł
    -0.10
    бав
    -0.10
     CLUB
    -0.10
    åĬ«
    -0.09
    åĵķ
    -0.09
    знаком
    -0.09
    éĢį
    -0.09
    vey
    -0.09
    é½
    -0.09
    POSITIVE LOGITS
    ~~~~
    0.08
    äºĺ
    0.08
    QA
    0.08
    PCI
    0.08
     Err
    0.08
    wards
    0.08
    è§īå¾Ĺèĩªå·±
    0.08
    formats
    0.07
     Denn
    0.07
    éĥģ
    0.07
    Activations Density 0.043%

    No Known Activations