© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    capacity building and training programs

    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
    éĢłç¦ı
    -0.11
     Aub
    -0.09
    ÑĢог
    -0.09
    åħĶ
    -0.08
    ä¸įåħĭ
    -0.08
    ksen
    -0.08
    pta
    -0.08
    åıijè¨Ģ人
    -0.08
    èļĮåŁł
    -0.08
    amba
    -0.08
    POSITIVE LOGITS
    ç²¾
    0.09
    éĤĭ
    0.08
    åĨĮ
    0.08
    èĥ¡åŃIJ
    0.08
    纳
    0.08
     wheels
    0.08
    -directory
    0.08
    涤
    0.08
    manship
    0.08
    æĥ³è±¡åĬĽ
    0.08
    Activations Density 0.028%

    No Known Activations