© 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. 27713
    Prev
    Next
    INDEX
    Explanations

    then followed by and

    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
    FACT
    -0.08
    æĢİä¹Īæīįèĥ½
    -0.07
    utz
    -0.07
    å¦Ĥä½ķéĢļè¿ĩ
    -0.07
    çļĦåIJĦ项
    -0.07
    ello
    -0.07
    .getRuntime
    -0.07
    .pull
    -0.07
    byname
    -0.07
    rawl
    -0.07
    POSITIVE LOGITS
    ä¸ĢæĹģçļĦ
    0.07
    èĭ¥æľī
    0.06
     invert
    0.06
    å°Ĩ该
    0.06
    åĨįåĬłä¸Ĭ
    0.06
    åĪ¶æĪIJ
    0.06
    亩
    0.06
    enso
    0.06
    ä¹Łä¸įçŁ¥
    0.06
     apply
    0.06
    Activations Density 0.125%

    No Known Activations