© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    programming syntax `erase`, `remove`, `;`

    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
    istro
    -0.08
    èij±
    -0.07
    allas
    -0.07
    æł¹æľ¬æĹłæ³ķ
    -0.07
    éĽ¾
    -0.07
    ych
    -0.07
    achter
    -0.07
    elage
    -0.07
    ä¸įåĩºæĿ¥
    -0.07
    à¹ģà¸Ĺ
    -0.06
    POSITIVE LOGITS
    éĢ¼
    0.08
     beant
    0.07
    inine
    0.07
     tolerant
    0.07
    ighton
    0.07
    æŁ¥
    0.07
     Lug
    0.07
    ç¼ĿéļĻ
    0.07
    è¶Ł
    0.07
    -target
    0.07
    Activations Density 0.002%

    No Known Activations