© 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. 33037
    Prev
    Next
    INDEX
    Explanations

    direction, downward, upward, left, right

    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
    ä¹ĭéĹ´çļĦåħ³ç³»
    -0.07
    ReadWrite
    -0.07
    级çļĦ
    -0.07
    ä¸Ĭ车
    -0.07
    Laugh
    -0.07
    åħį
    -0.07
    å¾Ĺèµ·
    -0.06
    羣åģĩ
    -0.06
    ubber
    -0.06
    æĮ¯åįİ
    -0.06
    POSITIVE LOGITS
    itta
    0.09
    æĸ¹åIJij
    0.08
     direction
    0.08
    ä¸ĢçĤ¹çĤ¹
    0.08
    ç®Ń头
    0.08
    æĸ¹åIJijçļĦ
    0.08
    à¹Ģà¸īียà¸ĩ
    0.08
    /left
    0.08
    åĬ²åĦ¿
    0.08
    /right
    0.08
    Activations Density 0.085%

    No Known Activations