© 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. 26070
    Prev
    Next
    INDEX
    Explanations

    Russian language fragments

    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
    ouri
    -0.08
    uston
    -0.08
    _NOTICE
    -0.07
    å¸ĥæŀĹ
    -0.07
    ä¸Ģ个女人
    -0.07
    ä¸Ģ个
    -0.07
    沧
    -0.07
    ampp
    -0.07
    inary
    -0.07
    iam
    -0.07
    POSITIVE LOGITS
    åĨ¤
    0.08
    kund
    0.07
    ç½ijç«Ļé¦ĸ页
    0.07
    æ°§éĩı
    0.07
    çĹħéŃĶ
    0.07
    allery
    0.07
    -many
    0.07
    asher
    0.07
    ç¿»
    0.07
    å±ħæĺĵ
    0.07
    Activations Density 0.497%

    No Known Activations