© 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. 54549
    Prev
    Next
    INDEX
    Explanations

    related to enzymes and foreign words

    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
    _NS
    -0.10
    天èĬ±
    -0.10
    éģģ
    -0.09
    IRS
    -0.09
    infra
    -0.09
    èĵĸ
    -0.09
    èĢ³
    -0.09
    ERC
    -0.09
    æłİ
    -0.08
     stere
    -0.08
    POSITIVE LOGITS
    æ´Ĺ涤
    0.11
    æ´Ĺè¡£æľº
    0.10
    heel
    0.08
    åĨµä¸Ķ
    0.08
    ä¸į解
    0.08
    樽
    0.08
    vc
    0.08
     Mitt
    0.08
     Hindi
    0.08
    缸åºĶ
    0.08
    Activations Density 0.133%

    No Known Activations