© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    specifications

    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
     label
    -0.07
    ossil
    -0.07
    MASK
    -0.07
     mam
    -0.07
    è¶Ĭ
    -0.06
    èĩ³äºİ
    -0.06
     Alias
    -0.06
     Label
    -0.06
    åĪĿ
    -0.06
    ARS
    -0.06
    POSITIVE LOGITS
    ä¸ŃåĽ½å®¶
    0.08
    اء
    0.08
    rypted
    0.07
    geist
    0.07
    izu
    0.07
    ille
    0.07
    fras
    0.07
    oppers
    0.07
    èĦ¾æ°Ķ
    0.07
    ivu
    0.07
    Activations Density 0.378%

    No Known Activations