© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16158
    Prev
    Next
    INDEX
    Explanations

    City | Center

    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
     mell
    -0.06
    çī¹å®ļ
    -0.06
    çĶ¨ä¹¦
    -0.06
    çĶ¨å¿ĥåİ»
    -0.06
    æ¦Ĥè¦ģ
    -0.06
    ml
    -0.06
    ļ
    -0.06
    ...
    -0.05
     relevant
    -0.05
    çĶ¨æīĭæĮĩ
    -0.05
    POSITIVE LOGITS
    abra
    0.08
    phan
    0.08
    à¸Ńยà¹Īาà¸ĩà¸Ķี
    0.08
    ä¸īæľŁ
    0.07
    िà¤ķा
    0.07
    ús
    0.07
    igits
    0.07
    ousy
    0.07
    heck
    0.07
    ewire
    0.07
    Activations Density 0.582%

    No Known Activations