© 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. 15229
    Prev
    Next
    INDEX
    Explanations

    ascending order

    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
    conte
    -0.08
     Lump
    -0.08
    é«ĺèĢ¸
    -0.08
    åºĶéħ¬
    -0.07
    ussin
    -0.07
    UGIN
    -0.07
    geist
    -0.07
    apar
    -0.07
    kad
    -0.07
    ä¸Ĭä¸Ģå±Ĥ楼
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    kbd
    0.08
    est
    0.08
    rement
    0.07
    -ish
    0.07
    lave
    0.06
    uess
    0.06
    ottom
    0.06
     order
    0.06
    顺åºı
    0.06
    Activations Density 0.006%

    No Known Activations