© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ansa
    -0.08
     harap
    -0.08
    either
    -0.07
    Ñĥго
    -0.07
    ESO
    -0.07
    illin
    -0.07
    éĹ¹
    -0.07
    Ģ
    -0.07
    Äı
    -0.07
    ÐĵÐĺ
    -0.07
    POSITIVE LOGITS
    ume
    0.08
    çłĶ究åĪ¶å®ļ
    0.07
    çĶ¨æĪ·æıIJä¾Ľ
    0.07
    orn
    0.07
    (always
    0.07
    åĪĨæŀIJä¸Ģä¸ĭ
    0.07
     knowledge
    0.07
    ux
    0.06
    um
    0.06
    æī¾ä¸Ģ个
    0.06
    Activations Density 0.005%

    No Known Activations