© 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. 1918
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun or concept

    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
    æĿĪ
    -0.09
    most
    -0.09
    sil
    -0.08
    æ¯Ķè¾ĥé«ĺ
    -0.08
    åĨįä¹Łæ²¡æľī
    -0.08
    åѦéĻ¢
    -0.08
    æªĢ
    -0.08
    éİ
    -0.08
    bounds
    -0.08
    ä¼ļä¼ļéķ¿
    -0.08
    POSITIVE LOGITS
    æµĵéĥģ
    0.09
    æµĵåİļ
    0.09
    æľĪä¸Ń
    0.09
    é»ĺå¥ij
    0.08
    è¿ĻèĪ¬
    0.08
    åĨ²æ´Ĺ
    0.08
    åĪļ
    0.08
    èĦĶ
    0.08
    è¿Ļç§į
    0.08
    ä¹±
    0.08
    Activations Density 0.122%

    No Known Activations