© 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. 49417
    Prev
    Next
    INDEX
    Explanations

    { `ROOT` `_DIR`

    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
    ammen
    -0.07
     EITHER
    -0.07
    åłĤ
    -0.07
    lieder
    -0.07
    iko
    -0.06
    esp
    -0.06
    çĭŃ
    -0.06
    adel
    -0.06
    akis
    -0.06
    iat
    -0.06
    POSITIVE LOGITS
    æľīæŶä¼ļ
    0.08
    æĽ´å¤ļ人
    0.07
    åĨįä¸Ĭæĸ°åı°éĺ¶
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    åħ¶ä»ĸçļĦ
    0.07
    ä»Ģä¹ĪçļĦ
    0.07
     other
    0.07
    ritti
    0.07
    åħ¶ä»ĸæĸ¹å¼ı
    0.07
    æľįåĬ¡çŃī
    0.07
    Activations Density 0.004%

    No Known Activations