© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 58619
    Prev
    Next
    INDEX
    Explanations

    application documentation or technical issues

    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
    Laugh
    -0.09
     Rage
    -0.09
     Bott
    -0.08
    çĵ¶é¢Ī
    -0.08
    ç²¾èĭ±
    -0.08
    ãģ¡ãĤĥãĤĵ
    -0.08
    æ®ļ
    -0.08
     pand
    -0.08
    elaide
    -0.08
    æħ°
    -0.08
    POSITIVE LOGITS
    èŀį
    0.10
     pur
    0.09
    Parm
    0.09
    alan
    0.08
    æĺĶ
    0.08
    pur
    0.08
    åIJĦè¡ĮåIJĦä¸ļ
    0.08
    격
    0.08
     Plug
    0.08
     ded
    0.08
    Activations Density 0.062%

    No Known Activations