© 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. 42916
    Prev
    Next
    INDEX
    Explanations

    scenic route, YA books, or Uber

    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
    项è§Ħå®ļ
    -0.08
    大èį¯æĪ¿
    -0.07
    ãģĺãĤģãģ¦
    -0.07
    stech
    -0.07
    éĩijé¦Ļ
    -0.07
    oplay
    -0.07
    çĻ¾è®¡
    -0.07
    долго
    -0.06
    ông
    -0.06
    ablish
    -0.06
    POSITIVE LOGITS
    æĬĸæĵŀ
    0.07
    سد
    0.06
    å·¡è§Ĩåijĺ
    0.06
    ловиÑĩ
    0.05
    æ·ĭæ¼ĵå°½
    0.05
    缮å½ķä¸Ģè§Ī
    0.05
    oggio
    0.05
    .TypeOf
    0.05
    çļĦæīĢæľīä½ľåĵģ
    0.05
    pper
    0.05
    Activations Density 5.090%

    No Known Activations