© 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. 49954
    Prev
    Next
    INDEX
    Explanations

    identifiers like GUIDs

    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
    arkin
    -0.07
    agged
    -0.07
    ky
    -0.07
    าà¸ģัà¸ļ
    -0.06
    ({},
    -0.06
    icum
    -0.06
    tus
    -0.06
    svar
    -0.06
    olin
    -0.06
    {}_
    -0.06
    POSITIVE LOGITS
    paces
    0.08
    æĹ¥æŃ¢
    0.07
    æ®ĥ
    0.07
    endl
    0.07
    åįĬå¤ľ
    0.07
     nutshell
    0.07
    ooth
    0.07
    注åĨĮèµĦéĩij
    0.07
    attro
    0.07
    模å¼ıçļĦ
    0.07
    Activations Density 0.076%

    No Known Activations