© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49315
    Prev
    Next
    INDEX
    Explanations

    related or unrelated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artet
    -0.07
    èı²çī¹
    -0.07
    anche
    -0.06
    ragt
    -0.06
     alike
    -0.06
    éĺħ读åħ¨æĸĩ
    -0.06
    å°±åĥıä¸Ģ个
    -0.06
    ç¡ķ士çĶŁ
    -0.06
    以åıĬä¸İ
    -0.06
    länd
    -0.06
    POSITIVE LOGITS
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    0.08
    è¿Ļåı¯èĥ½æĺ¯
    0.07
    æŁIJäºĽ
    0.07
    æĽ´ä¸įæĺ¯
    0.07
    ä¸įä¸Ģå®ļ
    0.07
    åı¯èĥ½ä¼ļ导èĩ´
    0.07
    çĦ¶æĺ¯
    0.07
    è°Īä¸įä¸Ĭ
    0.07
    å¢ŀå¼·
    0.07
     unrelated
    0.06
    Activations Density 0.001%

    No Known Activations