© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23440
    Prev
    Next
    INDEX
    Explanations

    cross-validation and bootstrap UI components

    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
    .writ
    -0.07
     qualific
    -0.07
    lena
    -0.07
    clid
    -0.07
     lobby
    -0.07
    [text
    -0.07
    lessness
    -0.07
    richter
    -0.07
     unintended
    -0.07
    ifica
    -0.07
    POSITIVE LOGITS
    æĸ¹æ³ķè¿Ľè¡Į
    0.08
     method
    0.08
     iterations
    0.08
    åľ¨åİŁ
    0.07
    _method
    0.07
    è¿Ń代
    0.07
    æĸ¹æ³ķ
    0.07
     Method
    0.07
    method
    0.07
    èī
    0.07
    Activations Density 0.014%

    No Known Activations