© 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. 41582
    Prev
    Next
    INDEX
    Explanations

    supposedly correct or incorrect

    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
     обо
    -0.08
    _authenticated
    -0.08
    éľĨ
    -0.07
    æĪIJæŃ£
    -0.07
    uel
    -0.07
    obuf
    -0.07
    ãĤĬè¿Ķ
    -0.07
    roda
    -0.07
    å°ĩä¾Ĩ
    -0.07
    rum
    -0.07
    POSITIVE LOGITS
    æĺİæĺİ
    0.11
     supposedly
    0.11
    æĺİæĺİæĺ¯
    0.11
    ä¸įåºĶ该
    0.10
     pourtant
    0.10
     correctly
    0.10
     supposed
    0.09
     ÑıкобÑĭ
    0.09
     correct
    0.09
     incorrectly
    0.09
    Activations Density 0.026%

    No Known Activations