© 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. 32159
    Prev
    Next
    INDEX
    Explanations

    probability of sequences and selections

    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
    ª
    -0.08
    çĶŁåij½è´¢äº§å®īåħ¨
    -0.07
    dev
    -0.07
    aint
    -0.07
    åģı
    -0.07
    以èĩ³äºİ
    -0.07
    åŁ
    -0.07
     dev
    -0.06
    inci
    -0.06
    pond
    -0.06
    POSITIVE LOGITS
     factor
    0.07
    choice
    0.07
     sebanyak
    0.07
    ÙĪاØŃ
    0.07
    åĨįèµ·
    0.07
    é¦ĸèµŀ
    0.07
     ÑĤÑĢой
    0.07
    绯
    0.07
    åĽłåŃIJ
    0.07
    ajok
    0.07
    Activations Density 0.010%

    No Known Activations