© 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. 10015
    Prev
    Next
    INDEX
    Explanations

    5% significance level

    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
     Cint
    -0.08
     farmace
    -0.07
    ToF
    -0.07
    åIJĥåĬĽ
    -0.07
    rach
    -0.07
    profil
    -0.07
    è¸Ĭè·ĥ
    -0.07
    steller
    -0.07
    clar
    -0.07
    AtIndex
    -0.07
    POSITIVE LOGITS
    reject
    0.07
    åħĪ
    0.07
     Ðijай
    0.07
    jub
    0.06
    ä¹İåħ¶
    0.06
    åĪĨå·¦åı³
    0.06
    è§ĦåĪĴ纲è¦ģ
    0.06
    ä¸ĢçıŃ
    0.06
    æĭľ
    0.06
    -split
    0.06
    Activations Density 0.002%

    No Known Activations