© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    desired target extraction

    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
    æĴŃ
    -0.07
    IENT
    -0.07
    ien
    -0.06
    ä»£æĽ¿
    -0.06
     Cra
    -0.06
    大æĺİ
    -0.06
    Oi
    -0.06
    广度
    -0.06
    .Exceptions
    -0.06
    åĴĭ
    -0.06
    POSITIVE LOGITS
    羣æŃ£
    0.11
    羣æŃ£çļĦ
    0.10
     desired
    0.10
     ÑģобÑģÑĤвенно
    0.10
     target
    0.09
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.09
    çļĦ羣æŃ£
    0.09
    ä½łæĥ³è¦ģçļĦ
    0.09
    _target
    0.09
    usable
    0.09
    Activations Density 0.301%

    No Known Activations