© 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. 50551
    Prev
    Next
    INDEX
    Explanations

    describing a condition

    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
    ä¸įç¦ģ
    -0.09
    æĢĢ念
    -0.09
    جÙĬÙĦ
    -0.09
    éĻ¡
    -0.09
     lá»Ŀi
    -0.08
    hung
    -0.08
    çģµ
    -0.08
    æ»ļæ»ļ
    -0.08
    ouver
    -0.08
    onnen
    -0.08
    POSITIVE LOGITS
    åĨµ
    0.10
    æ³ģ
    0.10
    åı«åģļ
    0.10
    ÌĢ
    0.09
    æ°Ľ
    0.09
    pecific
    0.09
    als
    0.09
    SEE
    0.09
    大éģĵ
    0.09
     Harrison
    0.09
    Activations Density 0.066%

    No Known Activations