© 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. 46000
    Prev
    Next
    INDEX
    Explanations

    federal family

    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
    é¢ĸ
    -0.07
    quo
    -0.07
    currently
    -0.06
    èĵī
    -0.06
    ifs
    -0.06
    åľ°é»Ħ
    -0.06
    åĪĨéĥ¨
    -0.06
    潦
    -0.06
     currently
    -0.06
    lesa
    -0.06
    POSITIVE LOGITS
    类似éĹ®é¢ĺ
    0.11
    类似çļĦ
    0.11
    .fm
    0.10
    类似
    0.10
     подобнÑĭÑħ
    0.10
     hasonló
    0.09
     indeed
    0.09
     serupa
    0.09
    ç¡®å®ŀ
    0.08
     подобнÑĭе
    0.08
    Activations Density 0.100%

    No Known Activations