© 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. 28674
    Prev
    Next
    INDEX
    Explanations

    right, left, or comparator

    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§ī
    -0.07
    ç»İ
    -0.07
    çĴŁ
    -0.06
    ç¦ıå¾·
    -0.06
     zlib
    -0.06
    sz
    -0.06
    äºĴ缸
    -0.06
    äºĴ为
    -0.06
    å°ıæĿ¿
    -0.06
    ÙĬØ«
    -0.06
    POSITIVE LOGITS
    à¹ģà¸Ĺà¸Ļ
    0.08
     вмеÑģÑĤо
    0.07
    ãĥģãĥ§
    0.07
    Coroutine
    0.07
    -tax
    0.07
    åīįæµ·
    0.07
    对ä¸Ĭè¿°
    0.07
    alti
    0.07
    anyon
    0.07
    oose
    0.07
    Activations Density 0.128%

    No Known Activations