© 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. 65455
    Prev
    Next
    INDEX
    Explanations

    legal and technical requirements

    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
    eldom
    -0.07
    irit
    -0.07
     wÅĤaÅĽnie
    -0.07
     bege
    -0.07
    embra
    -0.07
    èijµ
    -0.07
    çī¹æѤ
    -0.06
     appunto
    -0.06
    USAGE
    -0.06
    ìķ¤
    -0.06
    POSITIVE LOGITS
    管çIJĨæĸ¹éĿ¢
    0.07
    Ymd
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
    ciel
    0.06
    çŃīåħ¶ä»ĸ
    0.06
    YM
    0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.06
     دÛĮگرÛĮ
    0.06
    اÙĨÙĬ
    0.06
    ät
    0.06
    Activations Density 0.002%

    No Known Activations