© 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. 62705
    Prev
    Next
    INDEX
    Explanations

    after sign or another

    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
    entan
    -0.08
    zam
    -0.07
    chner
    -0.07
    elian
    -0.07
    umann
    -0.07
    ali
    -0.07
    iteli
    -0.07
    utz
    -0.07
    ussian
    -0.07
    zkod
    -0.07
    POSITIVE LOGITS
    åıĪä¸Ģ个
    0.11
    ë§Īëĭ¤
    0.09
    ãģĶãģ¨ãģ«
    0.09
    atat
    0.08
    åıĪä¸Ģ
    0.08
    ç®Ģç®Ģåįķ
    0.07
    æİ¥èijĹ
    0.07
    ìĶ©
    0.07
    _decorator
    0.07
    haps
    0.07
    Activations Density 0.076%

    No Known Activations