© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63942
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    er
    -0.09
    keit
    -0.09
    s
    -0.08
    à¹īà¸ĩ
    -0.08
    ibernate
    -0.08
    еÑĤ
    -0.08
    ÏĤ
    -0.08
    Ùijت
    -0.07
    Ø©
    -0.07
    ért
    -0.07
    POSITIVE LOGITS
    ejo
    0.09
    lı
    0.08
    ially
    0.08
    pil
    0.08
    éģĹçĹĩ
    0.08
    Occurred
    0.08
    ÑĤаж
    0.07
    мееÑĤÑģÑı
    0.07
    аниÑı
    0.07
    æ¯Ľæ³½ä¸ľ
    0.07
    Activations Density 0.399%

    No Known Activations