© 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. 19798
    Prev
    Next
    INDEX
    Explanations

    ending in ous or starting with typical

    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
    exter
    -0.09
    åī¯éĻ¢éķ¿
    -0.09
    /boot
    -0.09
    æ²½
    -0.09
    åł°
    -0.09
    好åIJĥ
    -0.09
    akt
    -0.09
    ä¸ŃæľĢ
    -0.09
    inton
    -0.08
    è¿ĩåİ»çļĦ
    -0.08
    POSITIVE LOGITS
    ä¸į解
    0.09
    èİľ
    0.09
     Finch
    0.08
    abus
    0.08
    æµģ失
    0.08
    é¥Ń
    0.08
    å·´å·´
    0.08
    åľ°ä¸Ńæµ·
    0.08
    _MAXIMUM
    0.08
    Atl
    0.08
    Activations Density 0.002%

    No Known Activations