© 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. 13643
    Prev
    Next
    INDEX
    Explanations

    long beach

    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
     ranked
    -0.06
    å¨ĵå¨ĵ
    -0.06
    并ä¸Ķè¿ĺ
    -0.06
    çĽ¸å¯¹æĿ¥è¯´
    -0.06
    \n
    -0.06
    _globals
    -0.06
     Relative
    -0.05
    \
    -0.05
    çĽ¸å¯¹æ¯Ķè¾ĥ
    -0.05
     rest
    -0.05
    POSITIVE LOGITS
    ebt
    0.08
    欢è¿İåħ³æ³¨
    0.08
    Ĵáŀ
    0.08
     nutris
    0.08
    estig
    0.08
    راج
    0.08
    ÏĥειÏĤ
    0.08
     laks
    0.08
    stellen
    0.08
    иÑģпÑĥÑģка
    0.08
    Activations Density 0.007%

    No Known Activations