© 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. 57821
    Prev
    Next
    INDEX
    Explanations

    City, Forest, street

    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
    æµ´
    -0.10
    åıijå±ķ模å¼ı
    -0.09
    ungs
    -0.09
    澡
    -0.09
    游åĩ»éĺŁ
    -0.09
    ãĥŀãĥ¼
    -0.09
    赤
    -0.09
    满äºĨ
    -0.09
    ä¸įåłª
    -0.08
    ç¡Į
    -0.08
    POSITIVE LOGITS
    igy
    0.09
    cape
    0.09
    alerts
    0.08
     Compilation
    0.08
    kop
    0.08
    产åѦ
    0.08
    egr
    0.08
    OLUM
    0.08
    pii
    0.08
    æģĭ
    0.08
    Activations Density 0.003%

    No Known Activations