© 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. 52770
    Prev
    Next
    INDEX
    Explanations

    is followed by descriptive words

    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
    åľ¨è¿Ļ个
    -0.09
    _strcmp
    -0.08
    åŃĺåľ¨äºİ
    -0.08
     indem
    -0.08
    ä¸ĢèĪ¬çļĦ
    -0.08
     Creed
    -0.08
     skÅĤad
    -0.07
     Kö
    -0.07
    ç´«
    -0.07
    麾
    -0.07
    POSITIVE LOGITS
    让å®ĥ
    0.10
    使ä¹ĭ
    0.09
    олж
    0.09
    æ§Ľ
    0.09
    æīĵæŀ¶
    0.09
    å¸Ĥåİ¿
    0.09
    riv
    0.08
    åħ¶ä»ĸçݩ家
    0.08
     ende
    0.08
    åħ´ä¸ļ
    0.08
    Activations Density 1.448%

    No Known Activations