© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    male, white, adult

    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
    åIJĪçIJĨåĮĸ
    -0.08
    cliffe
    -0.07
    mk
    -0.07
    trä
    -0.07
     berken
    -0.07
    umon
    -0.07
    yd
    -0.07
     **âĢŀ
    -0.07
    czyk
    -0.07
    _docs
    -0.07
    POSITIVE LOGITS
    çŃīçī¹çĤ¹
    0.10
    ãģĭãģ¤
    0.07
    并åħ·æľī
    0.07
    èĢĮä¸Ķæĺ¯
    0.06
    ä¸Ķåħ·æľī
    0.06
    æĹł
    0.06
     medium
    0.06
    çŃīä¼ĺçĤ¹
    0.06
    æľĢéĩįè¦ģçļĦæĺ¯
    0.06
    orp
    0.06
    Activations Density 0.231%

    No Known Activations