© 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. 41987
    Prev
    Next
    INDEX
    Explanations

    list or sequence?

    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
    agn
    -0.06
    Ñĥз
    -0.06
    å¥ī
    -0.06
    éĵ¶
    -0.06
    ucking
    -0.06
    uzzi
    -0.06
    uri
    -0.06
    ç®Ĺ
    -0.06
    é«ĺä½į
    -0.06
    ft
    -0.06
    POSITIVE LOGITS
    BuilderInterface
    0.08
    çĶŁç´ł
    0.08
    åįİé¾Ļ
    0.08
    æłijä¸Ģ
    0.08
    jord
    0.08
    .jasper
    0.07
    管çIJĨåıĬ
    0.07
    çīĪæĿĥåĿĩ
    0.07
    elain
    0.07
    janya
    0.07
    Activations Density 0.001%

    No Known Activations