© 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. 12640
    Prev
    Next
    INDEX
    Explanations

    where followed by he she they

    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
    éĩĮ没æľī
    -0.08
    rite
    -0.07
    orrent
    -0.07
    ë°ĺ
    -0.07
    å±ķæľĽæľªæĿ¥
    -0.07
    arz
    -0.07
    èIJ½å¹ķ
    -0.07
    è¿Ľç¤¾åĮº
    -0.07
    ÙĤÙĩ
    -0.07
    bah
    -0.07
    POSITIVE LOGITS
    upon
    0.10
     presumably
    0.09
     appunto
    0.07
    quiera
    0.07
    æĥ³å¿ħ
    0.07
    ç©į
    0.07
     it
    0.06
    ÑĤÑĸм
    0.06
    odzi
    0.06
    å®ĥ
    0.06
    Activations Density 0.164%

    No Known Activations