© 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. 18377
    Prev
    Next
    INDEX
    Explanations

    surnames and titles

    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
    gt
    -0.08
    eron
    -0.08
    ifting
    -0.07
    置身
    -0.07
    atang
    -0.07
    ament
    -0.07
    å³¥åµĺ
    -0.07
    åŀĭ
    -0.07
    çŀ»
    -0.07
    çľģå§Ķ书记
    -0.07
    POSITIVE LOGITS
     Jr
    0.13
    çĪµå£«
    0.12
     aka
    0.10
    iewicz
    0.09
     jr
    0.08
    ловиÑĩ
    0.08
    -Bold
    0.07
    baum
    0.07
    -Smith
    0.07
    escu
    0.07
    Activations Density 1.179%

    No Known Activations