© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52580
    Prev
    Next
    INDEX
    Explanations

    Star Wars franchise

    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
    å²IJ
    -0.08
    ä¸ĢèĦļ
    -0.08
    åĻ¨å®ĺ
    -0.08
    æĪIJé¾Ļ
    -0.08
    ç¥ŀ
    -0.08
    æŃ£å¼ı
    -0.08
    åī¯æľ¬
    -0.08
    dy
    -0.08
    ĺ认
    -0.08
     Blocking
    -0.08
    POSITIVE LOGITS
    ä¸Ńéĵģ
    0.10
    áo
    0.09
    ThanOr
    0.09
    enko
    0.09
    æĪĺå½¹
    0.08
    oxy
    0.08
    isd
    0.08
     thÆ°Æ¡ng
    0.08
    åħĨ
    0.08
    éĥ§
    0.08
    Activations Density 0.024%

    No Known Activations