© 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. 27468
    Prev
    Next
    INDEX
    Explanations

    document root

    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
    ungsk
    -0.08
    并éĿŀæĺ¯
    -0.07
     Lodge
    -0.07
     rasse
    -0.07
    ç«ŁçĦ¶
    -0.07
    å±ħçĦ¶
    -0.07
    åıĪä¸įæĺ¯
    -0.07
    å°±æľīåı¯èĥ½
    -0.07
    ÏĮδ
    -0.07
    åķ¬
    -0.06
    POSITIVE LOGITS
    asant
    0.08
    elpers
    0.08
    abei
    0.07
     disap
    0.07
    å
    0.07
    alice
    0.07
    hen
    0.07
    å¸Ĥéķĩ
    0.07
    åŀĴ
    0.07
    _PROC
    0.07
    Activations Density 0.114%

    No Known Activations