© 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. 9033
    Prev
    Next
    INDEX
    Explanations

    numbers, code, titles

    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
    -0.08
    j
    -0.07
    /
    -0.06
    ...
    -0.06
    &
    -0.06
    “
    -0.06
    èĩ¨
    -0.06
     “
    -0.06
    å¾Ī
    -0.06
    v
    -0.06
    POSITIVE LOGITS
    ÙħاÛĮÛĮ
    0.09
    ãĤŃãĥĵ
    0.09
    åħ¶ä»ĸæĸ¹å¼ı
    0.09
    FindObject
    0.09
    åħ¶æŀĹ
    0.09
    nok
    0.09
    cntl
    0.09
    åħĭç¦ı
    0.09
    Fizz
    0.08
    пиÑĤа
    0.08
    Activations Density 0.136%

    No Known Activations