© 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. 1262
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    Ø°
    -0.07
    Fr
    -0.07
     Fr
    -0.07
    oron
    -0.07
    è¯ģæĺİèĩªå·±
    -0.07
    设计ä¸Ĭ
    -0.06
     Mel
    -0.06
    循çݯ
    -0.06
     Cy
    -0.06
     Zub
    -0.06
    POSITIVE LOGITS
    iten
    0.07
    士æŀĹ
    0.07
    ilien
    0.07
    dios
    0.07
    =title
    0.07
    翼翼
    0.07
     (*((
    0.07
    ités
    0.06
    aveur
    0.06
    UNK
    0.06
    Activations Density 0.372%

    No Known Activations