© 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. 24986
    Prev
    Next
    INDEX
    Explanations

    method calls and variable access

    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
    æĪ·æĪ·
    -0.08
    ouver
    -0.07
    ActionCode
    -0.07
    èľľæ¡ĥ
    -0.07
     "&#
    -0.06
    gin
    -0.06
    èµ·åĽł
    -0.06
     FuÃŁ
    -0.06
    Foot
    -0.06
    igin
    -0.06
    POSITIVE LOGITS
    åŁ
    0.08
    æ³½
    0.08
    /from
    0.07
    .readValue
    0.07
    润
    0.07
     oy
    0.07
    folge
    0.07
    ANDLE
    0.07
    ints
    0.07
    ä½ĨæĦ¿
    0.07
    Activations Density 0.007%

    No Known Activations