© 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. 57724
    Prev
    Next
    INDEX
    Explanations

    letter Y

    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
    ury
    -0.07
    çļĨ
    -0.07
    bras
    -0.06
    ,
    -0.06
    ä¹Łéĥ½
    -0.06
    uran
    -0.06
    Y
    -0.06
    大家
    -0.06
    zt
    -0.05
     trans
    -0.05
    POSITIVE LOGITS
    Äĥtoare
    0.09
    arca
    0.09
    _Arg
    0.09
    Prostit
    0.09
     Antar
    0.08
    inator
    0.08
    дика
    0.08
    西åĮ»
    0.08
    èı²å°Ķå¾·
    0.08
    大åĪ©
    0.08
    Activations Density 0.005%

    No Known Activations