© 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. 30029
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    æ´ģ
    -0.07
    elo
    -0.06
    dd
    -0.06
    类似çļĦ
    -0.06
    C
    -0.06
    æĹĹé¼ĵ
    -0.06
     simil
    -0.06
    类似éĹ®é¢ĺ
    -0.06
    Ne
    -0.06
    ags
    -0.06
    POSITIVE LOGITS
    sus
    0.08
    ÑĢад
    0.08
    羣åģĩ
    0.08
    _DEFINE
    0.08
     Äijâu
    0.08
    afia
    0.08
     allegedly
    0.08
    åĮħ裹
    0.08
    .CONNECT
    0.07
    -num
    0.07
    Activations Density 0.283%

    No Known Activations