© 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. 10748
    Prev
    Next
    INDEX
    Explanations

    spectra, morphology, distribution

    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
    ç«ĭ足
    -0.08
    nier
    -0.08
    oufl
    -0.08
    ç«ĭ足äºİ
    -0.07
    quat
    -0.07
    è¿İ
    -0.07
    iksi
    -0.07
    achu
    -0.07
    è·¯åĮĹ
    -0.07
    onse
    -0.07
    POSITIVE LOGITS
     distributions
    0.10
    åĪĨéħįçļĦ
    0.08
     distribution
    0.08
    distribution
    0.08
    _distribution
    0.08
     distributing
    0.07
    Distribution
    0.07
    electron
    0.07
     DISTRIBUT
    0.07
     تÙĪزÙĬع
    0.07
    Activations Density 0.002%

    No Known Activations