© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    horizontal or vertical orientation

    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
    oles
    -0.08
    اء
    -0.08
    ÑģÑĤан
    -0.07
    çģ«äºĨ
    -0.07
     Giai
    -0.07
    äºĮ代
    -0.07
    èĪĨ
    -0.07
     Phase
    -0.07
    éĤ£ä»½
    -0.07
    asel
    -0.07
    POSITIVE LOGITS
    åŀĤ缴
    0.08
    /column
    0.07
    _blocking
    0.07
    icle
    0.07
     vertical
    0.07
    ç©¿è¿ĩ
    0.07
     horizontal
    0.07
    Vertical
    0.07
     Vertical
    0.07
    horizontal
    0.07
    Activations Density 0.013%

    No Known Activations