© 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. 31487
    Prev
    Next
    INDEX
    Explanations

    root directory

    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
    æ¦Ķ
    -0.08
    iances
    -0.08
    çĥŃéŨæłĩçŃ¾
    -0.08
    ções
    -0.08
    iable
    -0.08
    ments
    -0.08
    ç»Ŀ伦
    -0.07
    รà¹īาย
    -0.07
    odore
    -0.07
    tras
    -0.07
    POSITIVE LOGITS
    ä¸įæĭĶ
    0.11
    less
    0.10
    lings
    0.10
    rigues
    0.10
    lessness
    0.09
    é©
    0.08
    kits
    0.08
    iness
    0.08
    lessly
    0.08
    ADIUS
    0.08
    Activations Density 0.027%

    No Known Activations