© 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. 51249
    Prev
    Next
    INDEX
    Explanations

    .Convert, .Go, api, _id, _rate

    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
    ]bool
    -0.08
    ooth
    -0.08
    ä¸įæĢİä¹Ī
    -0.08
    pcf
    -0.08
    BOVE
    -0.07
    aN
    -0.07
    atico
    -0.07
    fru
    -0.07
    xdc
    -0.07
    agle
    -0.07
    POSITIVE LOGITS
    åķĨæĬ¥
    0.07
    ä½łå¥½
    0.06
    å¸ĤåľºçĽij管
    0.06
    çļĦéģĵçIJĨ
    0.06
     Daily
    0.06
    eret
    0.06
    âĢŀ
    0.06
    ãĤĤãģ£ãģ¨
    0.06
    ãĤĪãģĨ
    0.06
    绣çŃ¹æİ¨è¿Ľ
    0.06
    Activations Density 0.158%

    No Known Activations