© 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. 32245
    Prev
    Next
    INDEX
    Explanations

    ancestors and ancestry

    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
    vell
    -0.10
    à¸ĩาม
    -0.10
    teenth
    -0.10
    åIJİæİĴ
    -0.10
    åħħ足çļĦ
    -0.09
    elling
    -0.09
    atron
    -0.09
    åħ¬æĬ¥
    -0.09
    urm
    -0.09
    iken
    -0.09
    POSITIVE LOGITS
    ä¹İ
    0.10
    /custom
    0.10
    chaft
    0.09
    dì
    0.09
    åħ®
    0.09
     Äijá»ķ
    0.09
    -most
    0.09
    ä¸ī代
    0.09
    ously
    0.09
    们çļĦ
    0.08
    Activations Density 0.012%

    No Known Activations