© 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. 12682
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

    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
    lesia
    -0.08
    lese
    -0.08
    à¹Ħส
    -0.08
    UDI
    -0.08
    Ø°
    -0.08
    entes
    -0.07
    é¢Ĩ导åıĬ
    -0.07
    logen
    -0.07
    å¤ĸäºĭ
    -0.07
    umbu
    -0.07
    POSITIVE LOGITS
     exactly
    0.07
    Exactly
    0.07
    rite
    0.07
    æŃ£æĺ¯
    0.07
    æģ°
    0.07
    pir
    0.06
    å¯Ħ
    0.06
    ta
    0.06
    _SY
    0.06
    çīĽ
    0.06
    Activations Density 0.017%

    No Known Activations