© 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. 62114
    Prev
    Next
    INDEX
    Explanations

    equations with numbers and symbols

    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
    SYM
    -0.08
    çŃij
    -0.08
    _increment
    -0.08
    Õ²
    -0.07
    éħĿ
    -0.07
    _CONSTANT
    -0.07
    éħī
    -0.07
    设äºİ
    -0.07
    é¦ĸéķ¿
    -0.07
    ofi
    -0.07
    POSITIVE LOGITS
    åĪĨ解
    0.11
    æĭĨ
    0.09
     decom
    0.08
    split
    0.08
    åĪĴåĪĨ为
    0.08
     Decom
    0.08
    æĭĨåĪĨ
    0.08
     decomposition
    0.08
     cle
    0.08
    åĪĨè£Ĥ
    0.08
    Activations Density 0.007%

    No Known Activations