© 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. 46062
    Prev
    Next
    INDEX
    Explanations

    numbers, zero

    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
    çĥ¨
    -0.07
    .removeChild
    -0.07
    çĮ¾
    -0.07
    éªģ
    -0.07
    endam
    -0.07
    arend
    -0.07
    sem
    -0.07
    ello
    -0.06
    chter
    -0.06
    åıijèĩª
    -0.06
    POSITIVE LOGITS
     zero
    0.10
     cero
    0.10
    第ä¸ĢæľŁ
    0.09
    鼶
    0.09
     ZERO
    0.09
    ä¸ºéĽ¶
    0.09
    .zero
    0.08
     Zero
    0.08
    zero
    0.08
    .Zero
    0.08
    Activations Density 0.240%

    No Known Activations