© 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. 46710
    Prev
    Next
    INDEX
    Explanations

    citation identifiers

    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
    न
    -0.07
    .cwd
    -0.07
    زÙĨد
    -0.06
    æĥ³è¦ģ
    -0.06
    زد
    -0.06
    åıĮæīĭ
    -0.06
    æ¶īåıĬ
    -0.06
    Ø°
    -0.06
    ificate
    -0.06
    زÙħ
    -0.06
    POSITIVE LOGITS
    egner
    0.09
    æĬķéĢĴç®ĢåİĨ
    0.07
    voices
    0.07
    å¦ĸåŃ½
    0.07
    ç¬¬åĽĽåŃ£
    0.07
    alian
    0.07
    alani
    0.07
     Pou
    0.07
    ocoa
    0.07
     NSStringFromClass
    0.07
    Activations Density 0.082%

    No Known Activations