© 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. 17562
    Prev
    Next
    INDEX
    Explanations

    Jimmy and related names

    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
    <|box_end|>
    -0.09
    stown
    -0.08
    Allem
    -0.08
    mét
    -0.08
     módon
    -0.08
    kish
    -0.08
    ãģĶäºĪ
    -0.08
    edel
    -0.08
    raul
    -0.08
    eenth
    -0.08
    POSITIVE LOGITS
    ../../
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    iable
    0.07
    ehme
    0.06
    earch
    0.06
    iro
    0.06
     Cristo
    0.06
    omat
    0.06
    ÏĢη
    0.06
     plantilla
    0.06
    Activations Density 1.443%

    No Known Activations