© 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. 28975
    Prev
    Next
    INDEX
    Explanations

    Posted by or up

    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
    ł
    -0.12
    ï¸ı
    -0.11
    zinho
    -0.11
    acro
    -0.10
    berry
    -0.10
    earer
    -0.10
    tdown
    -0.10
    cratch
    -0.10
    ofire
    -0.10
    áŁĭ
    -0.10
    POSITIVE LOGITS
    ãĤĩãģĨ
    0.07
    lington
    0.07
    i
    0.07
    1
    0.06
    äºĨä¸Ģ
    0.06
    ãĤħãģĨ
    0.06
    à¹ĥà¸Ĭà¹īà¸ĩาà¸Ļ
    0.06
    èĩ³åħ³éĩįè¦ģçļĦä½ľçĶ¨
    0.06
    ب
    0.06
    ساÙħ
    0.06
    Activations Density 0.006%

    No Known Activations