© 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. 4250
    Prev
    Next
    INDEX
    Explanations

    job requirements

    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
    æ´Ĺ涤
    -0.10
    mars
    -0.10
    æİĮ
    -0.09
    åİĨ
    -0.09
    åı£ä¸Ń
    -0.09
    _pm
    -0.09
     staffing
    -0.09
    åľ°åĿª
    -0.09
    举
    -0.09
    ç»ĥ
    -0.09
    POSITIVE LOGITS
    ä¼ģä¸ļæıIJä¾Ľ
    0.10
    èij¡
    0.10
    æ¿Ĥ
    0.09
    社群
    0.09
    åħĢ
    0.08
    æİ¥åıĹéĩĩ访
    0.08
    æīįè¡Į
    0.08
    è¡Ģèħ¥
    0.08
    åľ¨æľªæĿ¥
    0.08
    stead
    0.08
    Activations Density 0.015%

    No Known Activations