© 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. 39616
    Prev
    Next
    INDEX
    Explanations

    biographical, events, tencent, nuclear, orangutan

    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
    iya
    -0.08
    æĨ¬
    -0.07
    ")}
    -0.07
    æĪªæŃ¢åĪ°
    -0.07
    reira
    -0.07
    ãģ¤ãģĭ
    -0.07
    ä¸įæĥĬ
    -0.07
    .gstatic
    -0.07
    ixin
    -0.07
    ç«£
    -0.07
    POSITIVE LOGITS
    upe
    0.07
    æĹħ
    0.06
    æĥij
    0.06
    pe
    0.06
    -to
    0.06
    im
    0.06
    uzz
    0.06
    ®
    0.06
    ÑĬÑİ
    0.06
     Far
    0.06
    Activations Density 0.004%

    No Known Activations