© 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. 23678
    Prev
    Next
    INDEX
    Explanations

    Frisco

    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
    çħ§æĺİ
    -0.09
     Mets
    -0.09
    æĢ»æī¿åĮħ
    -0.09
     thụ
    -0.09
    æī¿
    -0.08
    èģĶç³»æĸ¹å¼ı
    -0.08
     singapore
    -0.08
    .djang
    -0.08
    沧å·ŀ
    -0.08
    æĽ¼åŁİ
    -0.08
    POSITIVE LOGITS
    çŃīåľ°
    0.10
    è®Ń
    0.09
    è¥Ł
    0.08
     wr
    0.08
    è´§æºIJ
    0.08
    èıĬèĬ±
    0.08
    åĩºäºĨ
    0.08
    æķĪèĥ½
    0.08
    iska
    0.08
    rust
    0.08
    Activations Density 0.041%

    No Known Activations