© 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. 32895
    Prev
    Next
    INDEX
    Explanations

    new, related, same, aimed, keeping

    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
    å±İ
    -0.08
    uš
    -0.08
    æĥ³ä¸įåĪ°
    -0.07
    luit
    -0.07
    çĻ½çİī
    -0.07
    decor
    -0.07
     uitge
    -0.07
     ÐŁÐ¾Ð¿Ñĥ
    -0.07
    è®¤è®¤çľŁçľŁ
    -0.06
    .googleapis
    -0.06
    POSITIVE LOGITS
    å¾Īå¤ļçļĦ
    0.09
     Alright
    0.08
    wards
    0.08
    ä¼Ĺå¤ļçļĦ
    0.08
    åĽĽåĪĨ
    0.07
    æĽ´åĬłçļĦ
    0.07
    âĢIJ
    0.07
    IRE
    0.07
    ipher
    0.07
    жнÑı
    0.07
    Activations Density 0.002%

    No Known Activations