© 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. 27495
    Prev
    Next
    INDEX
    Explanations

    negation and exclusion

    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
    arto
    -0.08
    OnChange
    -0.08
    åĴĮæ°Ķ
    -0.07
    ingos
    -0.07
    RESSED
    -0.07
     "\""
    -0.07
    omad
    -0.07
     accompl
    -0.07
    пил
    -0.07
    家æľī
    -0.07
    POSITIVE LOGITS
     thereof
    0.09
    æĬĬä½łçļĦ
    0.06
    ãĢħ
    0.06
    ãģĿãģĨãģ§
    0.06
    Real
    0.06
    ukk
    0.06
    uber
    0.06
    ighth
    0.06
    Ģ
    0.06
    ience
    0.06
    Activations Density 0.203%

    No Known Activations