© 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. 39819
    Prev
    Next
    INDEX
    Explanations

    coordinate directions

    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
    å½ĵä¹ĭ
    -0.08
     juxtap
    -0.08
    çĴ
    -0.07
    راÛĮ
    -0.07
    æ·±ç§ĭ
    -0.07
    åĬłæ°Ķ
    -0.07
    -now
    -0.07
    åħĥæ°Ķ
    -0.07
    滨
    -0.07
    ernet
    -0.07
    POSITIVE LOGITS
    _EXTENSIONS
    0.08
     Wach
    0.07
    ä¹ı
    0.06
    åľ¨åħ¶ä¸Ń
    0.06
    ecat
    0.06
    illeurs
    0.06
     physical
    0.06
     untouched
    0.06
    ouz
    0.06
     Moff
    0.06
    Activations Density 0.002%

    No Known Activations