© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16275
    Prev
    Next
    INDEX
    Explanations

    CORRECT / RECT

    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
    èŁ
    -0.07
    çħ§
    -0.07
    ead
    -0.06
    agina
    -0.06
    ç¹ģ
    -0.06
     SW
    -0.06
    åħļæĶ¿
    -0.06
    Ĺ
    -0.06
     Hi
    -0.06
     Heights
    -0.06
    POSITIVE LOGITS
    volu
    0.08
    itled
    0.08
    osit
    0.07
    zheimer
    0.07
    è¦ģåģļåĪ°
    0.07
    otu
    0.07
    åIJĮæ¯Ķå¢ŀåĬł
    0.07
    ÏĦο
    0.07
    åħ·æľīçĭ¬ç«ĭ
    0.07
    -valu
    0.07
    Activations Density 0.003%

    No Known Activations