© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5627
    Prev
    Next
    INDEX
    Explanations

    content management CMS

    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
    serde
    -0.11
    itta
    -0.11
    èĨĽ
    -0.10
    çĵ¶
    -0.09
    åįķ车
    -0.09
    寡
    -0.09
    æ®ĭéħ·
    -0.09
    ë´ī
    -0.09
    åŁ¹åħ»åѦçĶŁ
    -0.08
    Py
    -0.08
    POSITIVE LOGITS
    æĸ°éĹ»åıijå¸ĥ
    0.09
    è§ī
    0.09
    åĪ°æľŁ
    0.09
    åĨįä¹Łä¸į
    0.09
    åĩºè¡Ģ
    0.09
     release
    0.09
     пед
    0.08
    åıĺåĬ¨
    0.08
     CMS
    0.08
    Release
    0.08
    Activations Density 0.143%

    No Known Activations