© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    French language and culture

    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
    omi
    -0.09
    SSION
    -0.09
    ilm
    -0.08
    itic
    -0.08
     sourceMappingURL
    -0.08
    anax
    -0.08
    owing
    -0.08
    çİ·
    -0.08
    aurus
    -0.08
    oha
    -0.08
    POSITIVE LOGITS
    ìĸ´
    0.13
    zeitig
    0.12
    ening
    0.11
    -speaking
    0.11
    ÑĤÑĢ
    0.10
    æ¹¾
    0.10
    stown
    0.10
    erv
    0.09
    åĨįéĢł
    0.09
    paces
    0.09
    Activations Density 0.022%

    No Known Activations