© 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. 31750
    Prev
    Next
    INDEX
    Explanations

    aiming for goals

    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
     بدÙĪرÙĩ
    -0.09
    åIJİ顾ä¹ĭ忧
    -0.08
    atos
    -0.07
     improperly
    -0.07
    ائØŃ
    -0.07
    .rawValue
    -0.07
    ä½łåį´
    -0.07
    æļĤè¡Į
    -0.07
    _lineno
    -0.07
    avage
    -0.07
    POSITIVE LOGITS
    çļĦ缮æłĩ
    0.10
    缮æłĩæĺ¯
    0.10
     targets
    0.10
    缮æłĩ
    0.09
    èĩªå·±çļĦ缮æłĩ
    0.09
    缮æłĩçļĦ
    0.08
     Targets
    0.08
    å°½åı¯èĥ½çļĦ
    0.08
    缮æ¨Ļ
    0.08
     goals
    0.08
    Activations Density 0.065%

    No Known Activations