© 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. 17222
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     only
    -0.06
    2
    -0.06
    ls
    -0.05
    1
    -0.05
    3
    -0.05
    åĨķ
    -0.05
    8
    -0.05
     No
    -0.05
     no
    -0.05
    ICAST
    -0.05
    POSITIVE LOGITS
    erat
    0.09
    erÃŃa
    0.08
    terer
    0.08
    ÄĽj
    0.08
    éĺ
    0.08
    æľ¬ç½ij
    0.08
    /--
    0.08
    buster
    0.08
    åħ¶è¡Į为
    0.08
    autoload
    0.07
    Activations Density 0.054%

    No Known Activations