© 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. 32200
    Prev
    Next
    INDEX
    Explanations

    native species and traditional

    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
    TÃľ
    -0.09
    éĶ
    -0.09
    ãģ«ãģı
    -0.08
     ìĿ´ë£¨
    -0.08
    æģŃ
    -0.08
    .Orientation
    -0.08
    -solid
    -0.08
    éĴº
    -0.08
    overs
    -0.08
    å¡ij
    -0.08
    POSITIVE LOGITS
    æľ¬åľŁ
    0.18
    æľ¬åľ°
    0.16
     indigenous
    0.14
     native
    0.13
    -native
    0.12
    çī¹èī²çļĦ
    0.11
    ä¹¡åľŁ
    0.11
    native
    0.11
    .getLocal
    0.11
    çī¹èī²
    0.11
    Activations Density 0.101%

    No Known Activations