© 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. 38448
    Prev
    Next
    INDEX
    Explanations

    alike or predicted

    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
    ierge
    -0.07
     afforded
    -0.07
     perm
    -0.06
     ";
    -0.06
     sollic
    -0.06
    è¯Ľä»Ļ
    -0.06
    _WARNINGS
    -0.06
     Hole
    -0.06
    actice
    -0.06
    æįŁ
    -0.06
    POSITIVE LOGITS
    æĩ¿
    0.08
    |$
    0.08
    anii
    0.08
    æĽ²åŃIJ
    0.08
    unci
    0.08
    丸
    0.07
    quential
    0.07
     VEND
    0.07
    å·²å©ļ
    0.07
    ÙİØ°
    0.07
    Activations Density 0.025%

    No Known Activations