© 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. 32942
    Prev
    Next
    INDEX
    Explanations

    associated with phrases

    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
    æľīæĿ¡ä»¶
    -0.10
    æĺ¼å¤ľ
    -0.10
    steen
    -0.09
    éĢģå¾Ģ
    -0.09
    ä¼ĺéĢī
    -0.09
    æĮĩ示
    -0.09
    è¿İ
    -0.09
    使èĢħ
    -0.09
    åİŁåĽłä¹ĭä¸Ģ
    -0.08
    ensis
    -0.08
    POSITIVE LOGITS
    æĻºèĥ½åĪ¶éĢł
    0.09
    æŁĶ
    0.09
     bir
    0.09
    çŃĸ
    0.09
    bir
    0.08
    ä¸ĭéĿ¢æĺ¯å°ı
    0.08
    ä¸Ģä¸ĭåŃIJ
    0.08
    è´ª
    0.08
     Brut
    0.08
    _cpp
    0.08
    Activations Density 0.022%

    No Known Activations