© 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. 46179
    Prev
    Next
    INDEX
    Explanations

    not real

    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
    andr
    -0.08
    aina
    -0.07
    ubil
    -0.07
    ogan
    -0.07
    %",
    -0.07
    ì¿
    -0.07
    çĽİ
    -0.07
    èħ¥
    -0.07
     chamb
    -0.07
    èħ®
    -0.06
    POSITIVE LOGITS
     actively
    0.10
    actively
    0.10
    主åĬ¨
    0.09
    sil
    0.09
    åĪ»æĦı
    0.09
    æķħæĦı
    0.09
     silence
    0.09
    æ²īé»ĺ
    0.09
     deliberate
    0.09
     intentional
    0.08
    Activations Density 0.141%

    No Known Activations