© 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. 24310
    Prev
    Next
    INDEX
    Explanations

    urls and links

    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
    epen
    -0.08
    draft
    -0.08
    èijĨ
    -0.07
    akta
    -0.07
    eper
    -0.07
    è¿Ļæł·çļĦä¸Ģ个
    -0.07
    aison
    -0.07
    _defs
    -0.07
    ittal
    -0.07
    ope
    -0.07
    POSITIVE LOGITS
    iac
    0.07
    å²Ľ
    0.07
    æľĪåľĨ
    0.07
    leden
    0.06
    åı£æīį
    0.06
     III
    0.06
    äºĨ解èĩªå·±
    0.06
    æľīç¼ĺ
    0.06
    III
    0.06
    ä»Ĩ
    0.06
    Activations Density 0.006%

    No Known Activations