© 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. 63396
    Prev
    Next
    INDEX
    Explanations

    dictionary and list option equals

    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
    ново
    -0.08
    宫å¤ĸ
    -0.08
    èĢĮåIJİ
    -0.07
    ανά
    -0.07
    课ä¸Ĭ
    -0.07
    并åıĸå¾Ĺ
    -0.07
    ego
    -0.07
    -0.07
     PRIM
    -0.07
    è²ł
    -0.07
    POSITIVE LOGITS
    æ»´æ°´
    0.07
    osto
    0.07
    StateChanged
    0.06
    clid
    0.06
    velte
    0.06
    éľ²æ°´
    0.06
    ellido
    0.06
     sworn
    0.06
    å¼Ĺ
    0.06
     dim
    0.06
    Activations Density 0.018%

    No Known Activations