© 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. 59099
    Prev
    Next
    INDEX
    Explanations

    go to places

    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
    åIJŀ
    -0.10
    CreateInfo
    -0.09
    ä¸Ģé¢Ĺ
    -0.09
    гоÑĢод
    -0.09
    彬
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.09
    稿
    -0.09
    èĥ¸åīį
    -0.09
    çĶ«
    -0.09
    èµ°ä¸ĭåİ»
    -0.09
    POSITIVE LOGITS
    åıĤåĬł
    0.11
    addtogroup
    0.09
    ald
    0.09
    åĪ°äºĨ
    0.09
     adventure
    0.08
     Adventure
    0.08
    estination
    0.08
    æłĮ
    0.08
    é£İæĻ¯åĮº
    0.08
    /run
    0.08
    Activations Density 0.030%

    No Known Activations