© 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. 51318
    Prev
    Next
    INDEX
    Explanations

    concluding statements

    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
    åĪĻä¼ļ
    -0.08
    åıįèĢĮä¼ļ
    -0.08
    aina
    -0.07
    kul
    -0.07
    æĹ©åľ¨
    -0.07
    èĥ½åĬ¨
    -0.07
    åıįèĢĮæĺ¯
    -0.07
    å±ħçĦ¶
    -0.07
    çĶļèĩ³ä¼ļ
    -0.07
    lut
    -0.06
    POSITIVE LOGITS
    arov
    0.07
     presumably
    0.07
    ượn
    0.07
    ä¸Ģè¿Ľ
    0.07
    ask
    0.07
    ¼
    0.07
    olo
    0.07
    èµ·æĿ¥äºĨ
    0.07
    ha
    0.06
    çĸ±
    0.06
    Activations Density 0.051%

    No Known Activations