© 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. 39199
    Prev
    Next
    INDEX
    Explanations

    auto generated or generates system

    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
     Gow
    -0.07
     Gom
    -0.07
    Õ¶
    -0.07
     Rep
    -0.07
    åĭ¤
    -0.07
    ÑģÑĤв
    -0.06
     Gór
    -0.06
    x
    -0.06
    æĪĺçļĦ
    -0.06
     Str
    -0.06
    POSITIVE LOGITS
    aran
    0.08
    oup
    0.08
    urusan
    0.08
    öd
    0.08
    izzi
    0.07
    Ñijд
    0.07
    åĪ¶å®ļæľ¬
    0.07
    owie
    0.07
    对èģĶ
    0.07
    çĶµåĻ¨æľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.001%

    No Known Activations