© 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. 4192
    Prev
    Next
    INDEX
    Explanations

    numeric sequences in code

    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
    ä¿
    -0.06
    å®ŀ
    -0.06
    åŁĭ
    -0.06
    ÃŃv
    -0.06
    æĮģ
    -0.06
    _transient
    -0.06
     Prime
    -0.06
    çŁ
    -0.05
     conv
    -0.05
    è¡
    -0.05
    POSITIVE LOGITS
    egg
    0.09
    æĸ°è¦ģæ±Ĥ
    0.08
     #=>
    0.08
    atchet
    0.08
    åĬłå¿«åıijå±ķ
    0.08
    ä¾ĽåĽ¾
    0.08
    ASTER
    0.08
    conde
    0.08
    Ế
    0.08
    _eof
    0.07
    Activations Density 0.008%

    No Known Activations