© 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. 19259
    Prev
    Next
    INDEX
    Explanations

    descriptive words followed by unrelated words

    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
    cmds
    -0.08
    olley
    -0.08
    ogan
    -0.08
    киÑı
    -0.08
    èijĨ
    -0.08
    éªı
    -0.08
    .scheme
    -0.07
    uchi
    -0.07
    sche
    -0.07
    çıĪ
    -0.07
    POSITIVE LOGITS
    op
    0.06
     ext
    0.05
    ilat
    0.05
    æıIJ
    0.05
     eb
    0.05
    åĴĮä¸ī
    0.05
    è£Ķ
    0.05
    åŃ¦ä¹łæķĻèĤ²
    0.05
    isant
    0.05
    cik
    0.05
    Activations Density 0.038%

    No Known Activations