© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    zero or 0

    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
    oris
    -0.07
    æĶĢæ¯Ķ
    -0.06
    secure
    -0.06
    alc
    -0.06
    è¿Ľè¡Įæ¯Ķè¾ĥ
    -0.06
    ench
    -0.06
    inkle
    -0.06
    åĸľ
    -0.06
    inat
    -0.06
    ernet
    -0.06
    POSITIVE LOGITS
    ä¸ºéĽ¶
    0.13
     zero
    0.11
    鼶
    0.11
     Zero
    0.10
    zero
    0.10
    ZERO
    0.10
    Zero
    0.10
    .Zero
    0.10
    _ZERO
    0.10
    鼶çĤ¹
    0.09
    Activations Density 0.016%

    No Known Activations