© 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. 34028
    Prev
    Next
    INDEX
    Explanations

    and

    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
    æĪĸ使çĶ¨
    -0.09
    æĪĸå°ı
    -0.08
    æĪĸéĥ¨åĪĨ
    -0.08
    æĪĸéĿŀ
    -0.08
    æĪĸå°ij
    -0.08
    æĪĸä¸İ
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    ож
    -0.07
    å¤©æ±ł
    -0.07
    доÑĢ
    -0.07
    POSITIVE LOGITS
    -and
    0.13
     &
    0.13
     and
    0.11
    _and
    0.10
     vÃł
    0.10
     AND
    0.10
    à¹ģละ
    0.09
    and
    0.09
     &&
    0.09
     и
    0.09
    Activations Density 0.265%

    No Known Activations