© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59120
    Prev
    Next
    INDEX
    Explanations

    speed, fast, slow, performance

    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
    éĻĦåĬł
    -0.10
    åĩºè·¯
    -0.09
    å¥Ĺ
    -0.09
    èĻ¬
    -0.09
    ä¸įå¼Ģ
    -0.08
    è°±
    -0.08
    ÙĤÙĬÙħ
    -0.08
    ä¸Ńè¶ħ
    -0.08
    çľ¼è§Ĵ
    -0.08
    asma
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦
    0.17
    æıIJéĢŁ
    0.15
     speed
    0.14
     speeds
    0.14
    çļĦéĢŁåº¦
    0.13
    æĢ§èĥ½
    0.12
     ÑģкоÑĢоÑģÑĤÑĮ
    0.12
    speed
    0.12
    Speed
    0.12
    peed
    0.12
    Activations Density 0.156%

    No Known Activations