© 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. 61636
    Prev
    Next
    INDEX
    Explanations

    negation or absence

    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
    geist
    -0.08
    боÑĢом
    -0.08
    ierra
    -0.08
     ulang
    -0.08
    ypes
    -0.07
    arrera
    -0.07
    ierna
    -0.07
    个åŃ©åŃIJ
    -0.07
    ãĥ³
    -0.07
    ournée
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.10
    bies
    0.09
    ness
    0.09
    æľŁå¾ĴåĪij
    0.09
    æļĩ
    0.08
    ë¦
    0.08
    iter
    0.08
     obstante
    0.08
    erg
    0.08
    ä¸ŃçĶŁ
    0.08
    Activations Density 0.003%

    No Known Activations