© 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. 50365
    Prev
    Next
    INDEX
    Explanations

    number bases

    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
    çĭĻåĩ»
    -0.07
    ä¿Ŀé²ľ
    -0.07
    ron
    -0.06
     despre
    -0.06
     Morg
    -0.06
     thinly
    -0.06
     Surf
    -0.06
     morg
    -0.06
     Kiss
    -0.06
    注å°Ħ
    -0.06
    POSITIVE LOGITS
    ifte
    0.08
    åĪ¶çļĦ
    0.07
    ancar
    0.07
    ugar
    0.07
    asers
    0.07
    DV
    0.07
    ASF
    0.07
    andom
    0.07
    ddl
    0.07
    ACES
    0.07
    Activations Density 0.019%

    No Known Activations