© 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. 54309
    Prev
    Next
    INDEX
    Explanations

    state followed by entities or roles

    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
    èĴ¿
    -0.09
    èĭ¦
    -0.08
    åŁİéĻħ
    -0.08
    幡
    -0.08
    æīĪ
    -0.08
    hid
    -0.08
    è¿Ļ个åIJįåŃĹ
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.08
    å¿«æį·
    -0.08
    çıŃéķ¿
    -0.08
    POSITIVE LOGITS
    à¸ļาล
    0.11
    lessness
    0.10
    hood
    0.09
    liness
    0.09
    ernes
    0.09
    craft
    0.09
    åĴĮ个人
    0.09
    opsis
    0.09
    less
    0.09
    ä¼¼
    0.09
    Activations Density 0.049%

    No Known Activations