© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    endt
    -0.08
    ilen
    -0.08
    -/
    -0.08
    âĢ¦**
    -0.08
    gard
    -0.08
    tee
    -0.08
    âĢ¦Â»
    -0.08
    >**
    -0.08
     fkk
    -0.08
    alom
    -0.08
    POSITIVE LOGITS
    ↵
    0.08
    ãĢĤ
    0.06
    浩浩
    0.06
    .
    0.06
    _plural
    0.06
    heiten
    0.05
    åľ£å¥³
    0.05
    __
    0.05
    èİİæĭī
    0.05
     boxed
    0.05
    Activations Density 0.152%

    No Known Activations