© 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. 2924
    Prev
    Next
    INDEX
    Explanations

    draft

    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
    åĢij
    -0.10
    主ä¸ļ
    -0.10
    Ľå»º
    -0.10
    hood
    -0.09
    èĦĨ
    -0.09
    ware
    -0.09
    ics
    -0.09
    ç»ıè´¸
    -0.09
    åľ¨æİ¥åıĹ
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    POSITIVE LOGITS
    åīįå¤ķ
    0.11
    ä¹ĭéĻħ
    0.09
    able
    0.09
    åľ°çĤ¹
    0.09
     adj
    0.09
    anel
    0.09
    åŃ£
    0.09
    æµģè¡ĮçļĦ
    0.09
    ä¸Ńãģ«
    0.09
     ави
    0.08
    Activations Density 0.009%

    No Known Activations