© 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. 38835
    Prev
    Next
    INDEX
    Explanations

    separators and structural elements

    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
    u
    -0.07
    çļĦä¸į
    -0.06
    3
    -0.06
    uai
    -0.06
     /
    -0.06
    hood
    -0.06
    as
    -0.06
     ...
    -0.05
    å¨Ħ
    -0.05
    hurst
    -0.05
    POSITIVE LOGITS
    IGA
    0.10
    orest
    0.09
    кона
    0.08
    नाव
    0.08
    -animate
    0.08
    enaire
    0.08
    ãģªãģıãģªãģ£ãģ¦
    0.08
    endant
    0.08
    hipster
    0.08
    OLO
    0.08
    Activations Density 0.001%

    No Known Activations