© 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. 56907
    Prev
    Next
    INDEX
    Explanations

    assignment and variable setting

    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
    è¡·
    -0.07
    ãĤĦãĤī
    -0.06
    veu
    -0.06
    omu
    -0.06
    AX
    -0.06
    mentation
    -0.06
    åľĨåľĨçļĦ
    -0.06
    inte
    -0.06
    cala
    -0.06
    å¹²
    -0.06
    POSITIVE LOGITS
    additional
    0.08
     additionally
    0.08
    é¢Ŀå¤ĸ
    0.08
    é¢Ŀå¤ĸçļĦ
    0.08
    å§Ĩæĸ¯
    0.07
    ä¸Ĭæ·»
    0.07
     additional
    0.07
     thêm
    0.07
    odate
    0.07
    ä¸Ńæ·»åĬł
    0.07
    Activations Density 0.039%

    No Known Activations