© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    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
    alic
    -0.07
    aying
    -0.07
    »
    -0.07
    ych
    -0.06
    ¹
    -0.06
    èĩ³é«ĺ
    -0.06
    çŁ³åĮĸ
    -0.06
    wargs
    -0.06
    ;</
    -0.06
     innings
    -0.06
    POSITIVE LOGITS
    ä¸įèĥ½å¤Ł
    0.08
    luan
    0.07
    innie
    0.07
    éģ´
    0.07
    hattan
    0.07
    åij½
    0.07
    evo
    0.07
     Explorer
    0.07
    reek
    0.07
    ioni
    0.07
    Activations Density 0.399%

    No Known Activations