© 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. 41553
    Prev
    Next
    INDEX
    Explanations

    size enough

    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
    duk
    -0.08
    agnol
    -0.08
    вики
    -0.07
    ANTS
    -0.07
    ινÏĮ
    -0.07
    áĢĦáĢºáĢ¸
    -0.07
    èİ«åIJįåħ¶
    -0.07
    .ConnectionString
    -0.07
    áĢĬáĢºáĢ¸
    -0.07
    æķħæĦı
    -0.07
    POSITIVE LOGITS
     manageable
    0.08
     enough
    0.07
    oner
    0.06
     SIL
    0.06
    awan
    0.06
    æĺ¯åı¯
    0.06
    ç»°
    0.06
    iba
    0.06
    _accept
    0.06
    ailable
    0.06
    Activations Density 0.027%

    No Known Activations