© 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. 61144
    Prev
    Next
    INDEX
    Explanations

    list of raw NavigationItem pointers

    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
     Joanna
    -0.06
     Sof
    -0.06
    ires
    -0.06
    åħ¸åŀĭçļĦ
    -0.05
     episod
    -0.05
    .fxml
    -0.05
    ecess
    -0.05
     Stall
    -0.05
    peration
    -0.05
    åIJ¬è¯Ŀ
    -0.05
    POSITIVE LOGITS
    ä¸įè¨Ģ
    0.08
    ily
    0.08
    alc
    0.08
    =__
    0.08
    åIJijèį£
    0.08
    GES
    0.08
    .innerWidth
    0.08
     ÑĢадÑĥ
    0.08
    íĺ¹
    0.07
    erst
    0.07
    Activations Density 0.160%

    No Known Activations