© 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. 32408
    Prev
    Next
    INDEX
    Explanations

    code context keywords

    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
     ‘
    -0.10
     “
    -0.09
    çĶ»
    -0.08
    ‘
    -0.08
    ’s
    -0.08
    eni
    -0.07
     drawn
    -0.07
    åħ»
    -0.07
    乡
    -0.07
    —an
    -0.07
    POSITIVE LOGITS
    幸ç¦ıå¿«ä¹IJ
    0.09
    adesh
    0.08
    zcze
    0.08
    ulette
    0.08
    ä¸ĢæľĿ
    0.07
    "..
    0.07
    tement
    0.07
    繩
    0.07
     kling
    0.07
    bish
    0.07
    Activations Density 0.046%

    No Known Activations