© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    json string

    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
     Zam
    -0.06
     оÑĩев
    -0.06
    举ç«Ļ
    -0.06
    éĺĶ
    -0.06
    çĽijåĪ¶
    -0.06
    istas
    -0.06
    onn
    -0.06
    奨
    -0.06
    aturday
    -0.06
     NSF
    -0.06
    POSITIVE LOGITS
    igers
    0.08
    εÏģι
    0.08
    iry
    0.08
    okit
    0.07
    egl
    0.07
    owska
    0.07
    çıŃå¹²éĥ¨
    0.07
    lap
    0.07
    onth
    0.07
    ifies
    0.07
    Activations Density 0.005%

    No Known Activations