© 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. 32212
    Prev
    Next
    INDEX
    Explanations

    and 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
    以å¾ħ
    -0.09
     unici
    -0.08
    guh
    -0.08
    gjeng
    -0.08
    .jquery
    -0.08
    åľ¨çľĭåĪ°
    -0.08
    FromClass
    -0.08
    lipp
    -0.08
    ÑĢко
    -0.08
    ç«ĭãģ£ãģŁ
    -0.08
    POSITIVE LOGITS
    nbsp
    0.10
    orra
    0.09
    vanced
    0.08
    жели
    0.07
    amental
    0.07
    å¾Ģ常ä¸Ģæł·
    0.07
    ppure
    0.07
    oczes
    0.07
    orre
    0.06
    igital
    0.06
    Activations Density 0.332%

    No Known Activations