© 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. 64011
    Prev
    Next
    INDEX
    Explanations

    The Bob Barker, Youtube, Sex

    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
    çĨŁäºĨ
    -0.08
    _Reference
    -0.07
    imeters
    -0.06
    arkt
    -0.06
     o
    -0.06
     rio
    -0.06
    -vers
    -0.06
    FileManager
    -0.06
    elerik
    -0.06
     Ashe
    -0.06
    POSITIVE LOGITS
    _sy
    0.08
    иÑģÑĤÑĢа
    0.07
    aisser
    0.07
    UMB
    0.07
    ÙĪاء
    0.07
    ottom
    0.07
    åĪĨä¸Ńå¿ĥ
    0.07
    sy
    0.07
     Prze
    0.07
    кÑĥда
    0.07
    Activations Density 0.682%

    No Known Activations