© 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. 46653
    Prev
    Next
    INDEX
    Explanations

    .wall, .com, numbers, programming code

    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
    len
    -0.06
    -
    -0.06
    å°ĺ
    -0.06
    Äį
    -0.06
    E
    -0.06
    ê»ĺ
    -0.06
    âĢij
    -0.05
    临
    -0.05
    ç½
    -0.05
     ribu
    -0.05
    POSITIVE LOGITS
    itest
    0.09
    argar
    0.08
    ierer
    0.08
    REAK
    0.08
     Feliz
    0.08
    åıĪ好
    0.08
    ialized
    0.08
    :Set
    0.08
    åŃ£åIJİ
    0.08
    anh
    0.08
    Activations Density 0.002%

    No Known Activations