© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers like int or String

    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
    为è¾ħ
    -0.08
    ont
    -0.07
    翱
    -0.07
    zzo
    -0.07
    ÏĮν
    -0.06
    tp
    -0.06
    åĵĪæĭī
    -0.06
    éĩįè¦ģä½ľçĶ¨
    -0.06
    itemap
    -0.06
    é£İåįİ
    -0.06
    POSITIVE LOGITS
    ecs
    0.07
    èĢĮåħ¥
    0.07
    acher
    0.07
    çŃĭ
    0.07
    жеÑĢе
    0.07
    uccio
    0.07
    otted
    0.07
    inke
    0.07
    ieder
    0.07
    ickl
    0.07
    Activations Density 0.001%

    No Known Activations