© 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. 14072
    Prev
    Next
    INDEX
    Explanations

    percentage signs and numbers

    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
    å¾Ĺèµ·
    -0.07
    ä¸įè¡Į
    -0.07
    rial
    -0.07
    иа
    -0.06
    .ceil
    -0.06
    orgh
    -0.06
    é©°
    -0.06
    acto
    -0.06
    è¾ŀ
    -0.06
     alphabet
    -0.06
    POSITIVE LOGITS
    ¬ģ
    0.09
    zun
    0.08
    åŁ¼
    0.08
    LN
    0.07
    alog
    0.07
    anat
    0.07
    andro
    0.07
    beck
    0.07
    hop
    0.07
    .pk
    0.07
    Activations Density 0.079%

    No Known Activations