© 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. 46835
    Prev
    Next
    INDEX
    Explanations

    surname segments

    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
     tact
    -0.08
    åĥ§
    -0.07
    补缺
    -0.07
    èĽĬ
    -0.07
    ç¨ļ
    -0.07
    çīĪ
    -0.07
    rex
    -0.06
    _DLL
    -0.06
    bn
    -0.06
    eded
    -0.06
    POSITIVE LOGITS
     family
    0.11
     család
    0.09
     families
    0.09
     famil
    0.08
    -family
    0.08
    family
    0.08
    _family
    0.08
    家åºŃçļĦ
    0.08
     surname
    0.08
    家åºŃ
    0.08
    Activations Density 0.427%

    No Known Activations