© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8417
    Prev
    Next
    INDEX
    Explanations

    Tulsa

    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
    nel
    -0.09
    èĤł
    -0.09
    ãģ¾ãģĦ
    -0.08
    ingly
    -0.08
    ä¹İ
    -0.08
    ollo
    -0.08
    lah
    -0.08
    è¤ļ
    -0.08
    hips
    -0.08
    asia
    -0.08
    POSITIVE LOGITS
    à¸Ľà¸£à¸°
    0.10
    è¿ĩçļĦ
    0.09
     viá»ĩc
    0.09
    ä¸ļ绩
    0.09
    /Runtime
    0.09
    нÑıÑĤ
    0.09
    æĿ¼
    0.09
    edo
    0.09
    就说
    0.09
     Reno
    0.09
    Activations Density 0.002%

    No Known Activations