© 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. 30373
    Prev
    Next
    INDEX
    Explanations

    return or output statements

    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
    åı£åŃIJ
    -0.08
     absor
    -0.08
    常èŃĺ
    -0.07
    ussen
    -0.07
    виÑĤ
    -0.07
     assorb
    -0.07
    常è¯Ĩ
    -0.07
     reliance
    -0.07
     Abs
    -0.07
     Trick
    -0.07
    POSITIVE LOGITS
    è¾ĵåĩº
    0.11
     output
    0.10
     berupa
    0.09
    output
    0.09
     Results
    0.09
     format
    0.09
    è¾ĵåĩºçĶµåİĭ
    0.09
    Output
    0.09
     Output
    0.08
     results
    0.08
    Activations Density 0.068%

    No Known Activations