© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    use and purpose

    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
    ople
    -0.07
    opl
    -0.06
    ron
    -0.06
    åĽ¾å½¢
    -0.06
    å¸ĥæĭī
    -0.06
    ssia
    -0.06
    èĭįèĮ«
    -0.06
    ãģ®ãĤ«
    -0.06
     grap
    -0.06
    太éĥİ
    -0.06
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.16
    åķĨä¸ļçĶ¨éĢĶ
    0.14
     purposes
    0.12
     اÙĦاستخداÙħ
    0.11
    缮çļĦçļĦ
    0.11
    urpose
    0.10
    çĶ¨å¤Ħ
    0.10
    à¸ģารà¹ĥà¸Ĭà¹īà¸ĩาà¸Ļ
    0.10
     PURPOSE
    0.10
    purpose
    0.10
    Activations Density 0.087%

    No Known Activations