© 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. 25739
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    ÑģмоÑĤÑĢи
    -0.08
    wat
    -0.08
    atetime
    -0.07
    azy
    -0.07
    ड़
    -0.07
     kalinya
    -0.07
    רת
    -0.07
    åį«çĶŁç»Ħç»ĩ
    -0.07
    StringValue
    -0.07
    fol
    -0.07
    POSITIVE LOGITS
    reece
    0.07
    å®ŀ绩
    0.06
     letz
    0.06
    elsea
    0.06
    Ïĥιά
    0.06
    ноÑģÑĤÑĢан
    0.06
    ловиÑĩ
    0.06
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.06
    erus
    0.05
    (OS
    0.05
    Activations Density 0.429%

    No Known Activations