© 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. 47160
    Prev
    Next
    INDEX
    Explanations

    numbers and variables

    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
    åIJij导
    -0.07
    群
    -0.07
    oxy
    -0.07
    .geo
    -0.07
    çļĦä¸Ģéĥ¨
    -0.06
     Rauch
    -0.06
    .band
    -0.06
    ../../
    -0.06
     Sahara
    -0.06
     Flick
    -0.06
    POSITIVE LOGITS
    yed
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    verte
    0.07
    жÑĥ
    0.07
    åıĹ人
    0.07
    utati
    0.07
     Kou
    0.06
    ÙĪاÙĩ
    0.06
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.06
    å°Ĩ该
    0.06
    Activations Density 0.009%

    No Known Activations