© 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. 28395
    Prev
    Next
    INDEX
    Explanations

    goal is to turn

    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
    icino
    -0.08
    abus
    -0.08
    upas
    -0.08
    [args
    -0.08
    oord
    -0.08
    onter
    -0.08
    ä¼ļ计
    -0.08
    adang
    -0.08
    наÑĩала
    -0.07
    MODULE
    -0.07
    POSITIVE LOGITS
     desirable
    0.08
     strategically
    0.08
    ä½łæĥ³è¦ģ
    0.08
     inc
    0.07
     engineered
    0.07
    çŃ¹æݪ
    0.07
    å·¥ç¨ĭ设计
    0.07
    å¦Ĥæŀľæĥ³
    0.07
    åľ¨è®¾è®¡
    0.07
     targeting
    0.07
    Activations Density 0.984%

    No Known Activations