© 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. 45118
    Prev
    Next
    INDEX
    Explanations

    category:

    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
    izm
    -0.09
    uze
    -0.08
    xim
    -0.08
    ehe
    -0.08
    漪
    -0.08
    åŃĹ第
    -0.08
    plier
    -0.08
    éĩijæ¦ľ
    -0.07
    otland
    -0.07
    éģįéĩİ
    -0.07
    POSITIVE LOGITS
    ys
    0.06
    æķ£
    0.06
    æķŀ
    0.06
    ysl
    0.06
     Prov
    0.06
    ixa
    0.06
    igi
    0.06
    éĹĬ
    0.06
     abd
    0.06
    prov
    0.06
    Activations Density 0.001%

    No Known Activations