© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7151
    Prev
    Next
    INDEX
    Explanations

    medical terms and technical commands

    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
    (pat
    -0.09
    æī¿
    -0.08
    aleb
    -0.08
    Tam
    -0.08
    /lang
    -0.07
    èĩªåľ¨
    -0.07
    LEG
    -0.07
    Orm
    -0.07
    odge
    -0.07
    iele
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.16
    两èĢħ
    0.15
    äºĮèĢħ
    0.13
    ä¿©
    0.13
     latter
    0.13
    åīįèĢħ
    0.10
    åıĮæĸ¹
    0.10
    两家
    0.09
    æłī
    0.09
    éĤ£ä¸ª
    0.09
    Activations Density 0.543%

    No Known Activations