© 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. 41075
    Prev
    Next
    INDEX
    Explanations

    non-destructive testing

    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
    飶
    -0.09
    ajang
    -0.08
    没æľīåĩºçİ°
    -0.08
    æĮģä¹ĭ以
    -0.08
    æĹ¥çº¿
    -0.08
    äºİä»Ĭå¹´
    -0.08
     Persist
    -0.08
     Persistence
    -0.08
    immel
    -0.08
    asons
    -0.08
    POSITIVE LOGITS
    å¹²æī°
    0.08
     вмеÑĪ
    0.08
    æľ¬èº«
    0.07
    æīĵæī°
    0.07
    çł´åĿı
    0.07
     interference
    0.07
    æĹłæįŁ
    0.07
    ä»ĭåħ¥
    0.07
     causing
    0.07
    å¹²é¢Ħ
    0.07
    Activations Density 0.072%

    No Known Activations