© 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. 33522
    Prev
    Next
    INDEX
    Explanations

    opposite directions

    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
    转移
    -0.08
    è¿ĩ渡
    -0.07
    ä¸įé«ĺ
    -0.07
     Gone
    -0.07
     transferred
    -0.07
    转移åĪ°
    -0.07
    ÙĩÙĨ
    -0.06
     Chal
    -0.06
    ehme
    -0.06
    ä¸ī项
    -0.06
    POSITIVE LOGITS
    irection
    0.11
    æĸ¹åIJij
    0.10
    æĸ¹åIJijçļĦ
    0.10
    direction
    0.10
    irectional
    0.10
    åıĮåIJij
    0.10
     direction
    0.10
    -direction
    0.10
    (back
    0.10
    =back
    0.09
    Activations Density 0.016%

    No Known Activations