© 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. 62167
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    Ùĩ
    -0.10
    ↵ ↵
    -0.10
    ,
    -0.09
    “
    -0.09
    -
    -0.08
    åIJİæīįèĥ½
    -0.08
    ↵  ↵
    -0.08
    —a
    -0.08
    ÙĬÙĨ
    -0.08
    çļĦä¸į
    -0.08
    POSITIVE LOGITS
     etc
    0.14
     illetve
    0.12
     namely
    0.11
     which
    0.10
     yaitu
    0.10
    以åıĬ
    0.10
     however
    0.10
    ãģĬãĤĪãģ³
    0.09
     valamint
    0.09
     respectively
    0.09
    Activations Density 3.246%

    No Known Activations