© 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. 47069
    Prev
    Next
    INDEX
    Explanations

    foreign names and words

    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
    olit
    -0.07
    ace
    -0.06
    .lex
    -0.06
    ãĤ¤ãĥĪ
    -0.06
    hlen
    -0.06
     traf
    -0.06
    æĦıæ°Ķ
    -0.06
    obot
    -0.06
    obe
    -0.06
    ä¸įå®Į
    -0.06
    POSITIVE LOGITS
    çŃīåĽ½éĻħ
    0.16
    åıijè¾¾åĽ½å®¶
    0.12
    èĭ±æĸĩ
    0.11
    欧ç¾İ
    0.11
    æĺ¯ç¾İåĽ½
    0.10
     foreign
    0.10
    西æĸ¹çļĦ
    0.10
    æݥ轨
    0.10
    西æĸ¹
    0.10
    èĢģå¤ĸ
    0.10
    Activations Density 0.502%

    No Known Activations