© 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. 62480
    Prev
    Next
    INDEX
    Explanations

    none or 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
     Med
    -0.07
    æİ¥æĽ¿
    -0.07
    med
    -0.07
    Cha
    -0.07
    proof
    -0.07
     chaotic
    -0.07
    çŃīä¼ĺåĬ¿
    -0.07
    Med
    -0.07
     Sisters
    -0.07
    oit
    -0.06
    POSITIVE LOGITS
    .none
    0.10
    æĹłä¸Ģ
    0.09
     none
    0.09
     ninguno
    0.08
    没æľīä¸Ģ个
    0.08
    æĢİä¹ĪåĬŀåij¢
    0.08
     NONE
    0.08
    NONE
    0.07
    æĢİä¹ĪåĬŀ
    0.07
    å¯Ĥå¯ŀ
    0.07
    Activations Density 0.024%

    No Known Activations