© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    code includes and namespaces

    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
    夫
    -0.07
    ish
    -0.07
    est
    -0.07
     Lec
    -0.07
    uze
    -0.06
    able
    -0.06
    ya
    -0.06
    iebe
    -0.06
    ho
    -0.06
    ep
    -0.06
    POSITIVE LOGITS
     lainnya
    0.08
    ldata
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
     other
    0.08
    缸è¾ħ缸æĪIJ
    0.08
     غÙĬرÙĩ
    0.08
    éĥijéĩį声æĺİ
    0.08
     otras
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
     otros
    0.07
    Activations Density 0.664%

    No Known Activations