© 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. 43402
    Prev
    Next
    INDEX
    Explanations

    range selection

    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
    ÙħÙĩ
    -0.07
    èī¯å¤ļ
    -0.07
    ril
    -0.07
    yl
    -0.07
    кÑĥл
    -0.06
    ambe
    -0.06
    ç¿Ĵ
    -0.06
    çĪ±å²Ĺ
    -0.06
    èģĮå®Ī
    -0.06
    æµij身
    -0.06
    POSITIVE LOGITS
    èĮĥåĽ´
    0.08
    -span
    0.08
    .beta
    0.08
    -range
    0.08
     span
    0.08
    èĮĥåĽ´åĨħçļĦ
    0.08
    ä»»æĦı
    0.07
    _span
    0.07
    èĮĥåĽ´åĨħ使çĶ¨
    0.07
    åĮºéĹ´
    0.07
    Activations Density 0.007%

    No Known Activations