© 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. 18352
    Prev
    Next
    INDEX
    Explanations

    surname endings in names

    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
    awah
    -0.07
    AW
    -0.07
    raad
    -0.06
    EQ
    -0.06
    身为
    -0.06
    年头
    -0.06
    arella
    -0.06
     Hung
    -0.06
     Blizzard
    -0.06
    ä¹ħä¹ĭ
    -0.06
    POSITIVE LOGITS
    izou
    0.08
    adx
    0.08
    çĪ±å²Ĺ
    0.08
    pecting
    0.07
     colleagues
    0.07
    ones
    0.07
    Ä«j
    0.07
    utnik
    0.07
    orney
    0.07
    ouns
    0.06
    Activations Density 0.082%

    No Known Activations