© 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. 20137
    Prev
    Next
    INDEX
    Explanations

    more information/details

    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
    fts
    -0.09
    5
    -0.09
    9
    -0.09
    èĢĮä¸Ķ
    -0.09
    åįĵ
    -0.09
    atra
    -0.08
    4
    -0.08
    å¾ģæ±Ĥ
    -0.08
    6
    -0.08
    oks
    -0.08
    POSITIVE LOGITS
    ç¯ģ
    0.09
    åıĹåĪ°å½±åĵį
    0.09
     sake
    0.08
    åIJ¯è¿ª
    0.08
    æŃ»è§Ĵ
    0.08
    éĽ¶é£Ł
    0.08
    é½ij
    0.08
    é£Ļ
    0.08
    semb
    0.08
    åĩłä¹İæĺ¯
    0.08
    Activations Density 0.026%

    No Known Activations