© 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. 34161
    Prev
    Next
    INDEX
    Explanations

    particles orient, expand, freeze, stiffen, keep, spread, coapt, die, sink

    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
     messing
    -0.08
    å·²å°Ĩ
    -0.08
    çĶ¨å¿ĥ
    -0.08
    é£Ľãģ°
    -0.07
    .started
    -0.07
    èĤ¯å®ļäºĨ
    -0.07
    å¾Ĺå¿ĥåºĶæīĭ
    -0.07
    æµĵåİļ
    -0.07
    angan
    -0.07
    å·²ç»ıè¿ĩåİ»
    -0.07
    POSITIVE LOGITS
     undergo
    0.09
     become
    0.08
    Opts
    0.07
    æĮīçħ§è§Ħå®ļ
    0.07
    æĿ¥ä¸ª
    0.07
     behave
    0.07
    bec
    0.07
    åıĺå¾Ĺ
    0.07
    irms
    0.07
    lug
    0.07
    Activations Density 0.218%

    No Known Activations