© 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. 27158
    Prev
    Next
    INDEX
    Explanations

    stroke rehabilitation

    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
    麻çĥ¦
    -0.09
    å·¡
    -0.09
    xae
    -0.08
    åıijçİ°äºĨ
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
     Integral
    -0.08
    社群
    -0.08
    æĦŁæŁĵ
    -0.08
    声
    -0.08
    .extra
    -0.08
    POSITIVE LOGITS
    elig
    0.10
    éĸ£
    0.09
    ç§ijæĬĢè¿ĽæŃ¥
    0.09
    请æĤ¨
    0.09
    å¥Ĺè£ħ
    0.09
    é¡¿
    0.09
    è¿ĽæŃ¥
    0.09
    âĨĶ
    0.09
    éĵ°
    0.09
    NEWS
    0.09
    Activations Density 0.167%

    No Known Activations