© 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. 56212
    Prev
    Next
    INDEX
    Explanations

    below is a

    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
    ãĤ¥
    -0.08
    indest
    -0.07
    à¹ĥ
    -0.07
    TimeZone
    -0.07
    æıIJé«ĺæķĪçİĩ
    -0.07
     viss
    -0.07
    ÑģлÑĥжа
    -0.07
    à¸ĵà¹Į
    -0.07
    çŃīä»Ģä¹Ī
    -0.07
    باد
    -0.07
    POSITIVE LOGITS
    ined
    0.08
    Kem
    0.07
     carefully
    0.07
    utow
    0.07
    าà¸Ĺ
    0.07
    ×ķ×¢
    0.07
    åĮħåIJ«äºĨ
    0.07
    çĦ¶åIJİåıĪ
    0.07
    ry
    0.06
    çĦ¶åIJİå°±
    0.06
    Activations Density 0.008%

    No Known Activations