© 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. 48417
    Prev
    Next
    INDEX
    Explanations

    numbers and programming

    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
    纯èī²
    -0.07
     Gale
    -0.07
     invaded
    -0.07
    ä¸Ńå±Ĥ
    -0.07
    åı°ä¸Ń
    -0.06
    Z
    -0.06
    æľĪä¸Ĭ
    -0.06
    å¤Ħå¤Ħ
    -0.06
    ä¸ĩåį·
    -0.06
    arg
    -0.06
    POSITIVE LOGITS
    uno
    0.08
     fours
    0.08
     Countdown
    0.08
    ä¸įæĮī
    0.08
    ίÏĥ
    0.08
     kreativ
    0.08
    ITED
    0.08
    è¿Ļ个æķ°åŃĹ
    0.07
    angka
    0.07
    bos
    0.07
    Activations Density 0.008%

    No Known Activations