© 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. 9478
    Prev
    Next
    INDEX
    Explanations

    discussing underlying values and priorities

    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
     conclusive
    -0.07
    eiro
    -0.07
    ç»ĵåIJĪå®ŀéĻħ
    -0.07
     pire
    -0.07
    ^{
    -0.06
    åĿıäºĭ
    -0.06
    说æľī
    -0.06
     vas
    -0.06
    æĮīçħ§è§Ħå®ļ
    -0.06
    æĤ²æĥ¨
    -0.06
    POSITIVE LOGITS
    åıįæĺłåĩº
    0.10
     priorities
    0.09
    ä½ĵçİ°åĩº
    0.09
    æ·±å±Ĥ
    0.09
     underlying
    0.09
    èĥĮåIJİ
    0.09
    æĬĺå°Ħ
    0.08
    ä½ĵçİ°äºĨ
    0.08
     values
    0.08
     broader
    0.08
    Activations Density 0.130%

    No Known Activations