© 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. 29343
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    aline
    -0.08
    ehme
    -0.08
    _buffers
    -0.07
     Sands
    -0.07
    agit
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    ibu
    -0.07
    rint
    -0.07
    Ascending
    -0.07
    ETY
    -0.07
    POSITIVE LOGITS
    å½ĵçĦ¶æĺ¯
    0.07
    åī¯
    0.07
     Cli
    0.07
    ijs
    0.07
    å°±æĺ¯
    0.07
    æłĩåĩĨ
    0.07
    å°±æĺ¯æĪij们çļĦ
    0.07
    è¿Ļå°±æĺ¯
    0.07
    éĻ¤äºĨåľ¨
    0.07
    _STANDARD
    0.07
    Activations Density 0.569%

    No Known Activations