© 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. 62641
    Prev
    Next
    INDEX
    Explanations

    commas separating items

    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
    /rfc
    -0.07
    åĮºåĮº
    -0.07
    utor
    -0.07
    akon
    -0.06
    ideon
    -0.06
    -Shirt
    -0.06
     ÙĨاد
    -0.06
    andbox
    -0.06
    åľ¨ä¸¤
    -0.06
    perimental
    -0.06
    POSITIVE LOGITS
    å®ļåĪ¶
    0.07
    åįģ大
    0.07
    ough
    0.07
    stellungen
    0.07
    *</
    0.07
    åħ¬çĪµ
    0.07
    åĸľ
    0.07
    禧
    0.06
    IMA
    0.06
    stell
    0.06
    Activations Density 0.052%

    No Known Activations