© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63774
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
    åĵī
    -0.06
    è¿Ļå°Ĩ
    -0.06
    ä¹ĭäºĮ
    -0.06
    ilo
    -0.06
    ee
    -0.06
    ansom
    -0.06
    ub
    -0.06
     mire
    -0.06
    èī
    -0.06
    è¿Ļä¸įä»ħ
    -0.06
    POSITIVE LOGITS
    åľ¨æŁIJ
    0.10
    è¯´ä½ł
    0.08
    æŁIJ
    0.08
    ordova
    0.08
    nick
    0.08
    رة
    0.08
    rone
    0.08
    еÑģп
    0.08
    rames
    0.08
    loor
    0.08
    Activations Density 0.041%

    No Known Activations