© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23713
    Prev
    Next
    INDEX
    Explanations

    string

    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
    indh
    -0.08
    å¦ĤæĹł
    -0.08
    oren
    -0.07
    erland
    -0.07
     caring
    -0.07
    oring
    -0.06
     killers
    -0.06
     Rücks
    -0.06
    offsetof
    -0.06
    avais
    -0.06
    POSITIVE LOGITS
    Encoded
    0.08
    æĸĩåŃĹ
    0.08
     quotes
    0.08
    .lines
    0.08
    åŃĹ符串
    0.08
    .string
    0.08
    许åı¯è¯ģ
    0.08
    -string
    0.08
    åĨħ容为
    0.08
    _strlen
    0.07
    Activations Density 0.357%

    No Known Activations