© 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. 49087
    Prev
    Next
    INDEX
    Explanations

    server name

    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
     "
    -0.07
    itable
    -0.06
    ilit
    -0.06
    åįĴ
    -0.06
    ians
    -0.06
    äºĨä¸Ģåı£
    -0.05
     at
    -0.05
    çļĦéĿĴ
    -0.05
    grave
    -0.05
    ç¬
    -0.05
    POSITIVE LOGITS
    oyer
    0.08
    ErrorResponse
    0.08
    elor
    0.08
    anko
    0.08
    âĢ¦]
    0.08
    æģ©
    0.07
    _ALIGNMENT
    0.07
    ×ĺר
    0.07
    ä¸ĥåįģäºĮ
    0.07
    úb
    0.07
    Activations Density 0.001%

    No Known Activations