© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    codes and specific terms

    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
    vier
    -0.08
    Ñĩини
    -0.07
    ä¸Ģä¸įå°ıå¿ĥ
    -0.07
    chtet
    -0.07
    zburg
    -0.07
    çħ¦
    -0.07
    rrha
    -0.07
    shima
    -0.07
    天åı°
    -0.07
    ç»®
    -0.07
    POSITIVE LOGITS
    èĢ¶
    0.07
    iglio
    0.07
    ipple
    0.06
    ForKey
    0.06
    ili
    0.06
    ásra
    0.06
    ucks
    0.06
    PM
    0.06
    çļĦç»ĵæŀľ
    0.06
    ÏĨη
    0.06
    Activations Density 0.017%

    No Known Activations