© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19778
    Prev
    Next
    INDEX
    Explanations

    touch or contact

    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
    对ä»ĺ
    -0.08
     Bale
    -0.08
    ologue
    -0.08
    MBER
    -0.08
    duct
    -0.08
    è¿ĩåī©
    -0.08
    èľľ
    -0.08
    ibox
    -0.08
    /prom
    -0.08
    åľ¨è¿Ļ个
    -0.08
    POSITIVE LOGITS
    å¥ı
    0.09
    综
    0.09
    ãĤ¬ãĤ¤
    0.09
    è¯ķåį·
    0.09
    (touch
    0.09
    ç¤ģ
    0.09
    .dy
    0.09
    å£ģåŀĴ
    0.09
    觸
    0.08
    redi
    0.08
    Activations Density 0.046%

    No Known Activations