© 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. 2453
    Prev
    Next
    INDEX
    Explanations

    association of

    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
    lines
    -0.09
    屿
    -0.09
    zer
    -0.08
    ắp
    -0.08
    é¢Ĺ
    -0.08
    æ¯Ĥ
    -0.08
    绿水éĿĴå±±
    -0.08
    astic
    -0.08
    ners
    -0.08
    labs
    -0.08
    POSITIVE LOGITS
    åī¯ä¼ļéķ¿
    0.11
    -wide
    0.10
    overs
    0.09
    ¡
    0.09
    ships
    0.09
    ively
    0.09
    łģ
    0.09
    ief
    0.09
     Downs
    0.09
     chÃłng
    0.09
    Activations Density 0.085%

    No Known Activations