© 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. 32768
    Prev
    Next
    INDEX
    Explanations

    walked into, responsibilities, war

    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
    ç§ĺ
    -0.08
    åŀ£
    -0.07
    adge
    -0.07
    ç¿»è¯ijæĪIJ
    -0.07
    åıĺæĽ´é¡¹çĽ®
    -0.07
    itol
    -0.07
    psy
    -0.07
    è²ī
    -0.07
    ilai
    -0.07
    wak
    -0.07
    POSITIVE LOGITS
    以轻
    0.06
    “As
    0.06
    ayer
    0.06
     rob
    0.06
    ÑĪеÑĤ
    0.06
    çĸĻçĺ©
    0.06
    ä¼łæĴŃ
    0.06
    åIJĮåı°
    0.06
    æĮļ
    0.06
    _ASSOC
    0.06
    Activations Density 0.015%

    No Known Activations