© 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. 9042
    Prev
    Next
    INDEX
    Explanations

    duplicate handling

    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
    è¦ģä¹Īæĺ¯
    -0.08
    åħ³æ³¨èĢħ
    -0.08
    erto
    -0.08
    ä¸Ģéĥİ
    -0.08
    Either
    -0.07
     Cott
    -0.07
    è¦ģä¹Ī
    -0.07
    upart
    -0.07
    apter
    -0.07
    _annotations
    -0.07
    POSITIVE LOGITS
     duplicate
    0.07
    åį«çĶŁ
    0.07
     repet
    0.07
     manual
    0.07
    åĪ¤
    0.07
    éķ¿æŶéĹ´
    0.07
     str
    0.06
    èĦı
    0.06
     handling
    0.06
    éĩįå¤į
    0.06
    Activations Density 0.011%

    No Known Activations