© 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. 34201
    Prev
    Next
    INDEX
    Explanations

    reporting verbs and negation

    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
     lej
    -0.08
    æĸ¯åŁº
    -0.07
    ingo
    -0.07
    è§Ĩéķľ
    -0.07
    klik
    -0.07
     enslaved
    -0.07
    ego
    -0.07
    _ready
    -0.07
    ibur
    -0.06
     slashing
    -0.06
    POSITIVE LOGITS
     acceptable
    0.08
    对人çļĦ
    0.07
     diganti
    0.07
     Kraj
    0.07
     cấp
    0.07
    åĢ¼æĺ¯
    0.07
    åĨĽä¸Ń
    0.07
     issue
    0.07
    اعÙĬ
    0.07
    æį¢æĪIJ
    0.06
    Activations Density 0.001%

    No Known Activations