© 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. 14451
    Prev
    Next
    INDEX
    Explanations

    unified approach or framework

    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
    nière
    -0.08
    èļª
    -0.08
    alog
    -0.08
    tery
    -0.08
    bones
    -0.07
    é£İéľľ
    -0.07
    -long
    -0.07
    leter
    -0.07
    _mut
    -0.07
    累累
    -0.07
    POSITIVE LOGITS
    itarian
    0.10
    -sama
    0.10
    -minded
    0.10
    æĢĿæĥ³è®¤è¯Ĩ
    0.08
    åľ¨ä¸Ģèµ·çļĦ
    0.08
     Sache
    0.08
    绣ä¸ĢçļĦ
    0.08
     minded
    0.08
    åĪ°ä¸Ģèµ·
    0.08
    lander
    0.07
    Activations Density 0.040%

    No Known Activations