© 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. 17070
    Prev
    Next
    INDEX
    Explanations

    reach to

    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
    èĴĻ
    -0.10
    åħģ
    -0.10
    adow
    -0.09
    纸ä¸Ĭ
    -0.08
    acas
    -0.08
    ìŀ¡
    -0.08
    침
    -0.08
    Ñģки
    -0.08
    edin
    -0.08
    ogn
    -0.08
    POSITIVE LOGITS
    éģĩåĪ°äºĨ
    0.10
    åĪ°æĿ¥
    0.10
    碰åĪ°
    0.10
    尽头
    0.10
    æĬ¤æłı
    0.09
    åĪ°äºĨ
    0.09
    æĿ¥åĪ°äºĨ
    0.09
     encountering
    0.09
    æĴŃæĬ¥
    0.09
     where
    0.09
    Activations Density 0.081%

    No Known Activations