© 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. 65251
    Prev
    Next
    INDEX
    Explanations

    create alias or remove duplicate

    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
    å°ıçľĭ
    -0.09
    utc
    -0.08
    emic
    -0.08
    viol
    -0.08
    usst
    -0.07
    渲
    -0.07
    åħ¨ä½ĵä¼ļè®®
    -0.07
    mica
    -0.07
    ril
    -0.07
    boom
    -0.07
    POSITIVE LOGITS
    ç»®
    0.08
    綺
    0.08
     пÑĢоде
    0.07
    ÑħождениÑı
    0.07
    失
    0.07
    ç´į
    0.06
    _CONTAINER
    0.06
     Fras
    0.06
    _dirty
    0.06
    æ£Ģçĸ«
    0.06
    Activations Density 0.158%

    No Known Activations