© 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. 48337
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic operations

    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
    éĩij森
    -0.08
    ×ķ×ķת
    -0.08
    æĺ¯ä¸įå¤Ł
    -0.08
    ewa
    -0.08
    shaw
    -0.08
    åѦäºĨ
    -0.08
    agin
    -0.08
    .nlm
    -0.08
    ölt
    -0.07
    _Run
    -0.07
    POSITIVE LOGITS
    XR
    0.06
     Kirby
    0.06
     noc
    0.06
    ç½ijåıĭ
    0.06
    æ´ŀ
    0.06
    æĻĵæĺİ
    0.05
     ing
    0.05
     nob
    0.05
     Gir
    0.05
    å®ĪåĢĻ
    0.05
    Activations Density 0.014%

    No Known Activations