© 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. 63568
    Prev
    Next
    INDEX
    Explanations

    format, document, node

    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
    вок
    -0.09
    cec
    -0.07
    rene
    -0.07
    mog
    -0.07
    pek
    -0.07
    åĤ»åŃIJ
    -0.07
    vl
    -0.06
    soc
    -0.06
    ç¬ĭ
    -0.06
    va
    -0.06
    POSITIVE LOGITS
    æł·
    0.08
    éªĦåĤ²
    0.08
    erschap
    0.07
    çIJ
    0.07
    `;
    0.07
    ("/",
    0.06
    éĺħ读éĩı
    0.06
     magát
    0.06
    eric
    0.06
    uing
    0.06
    Activations Density 0.058%

    No Known Activations