© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62988
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers ending in commas or question marks

    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
    ")[
    -0.08
    aupt
    -0.08
    estes
    -0.08
    èī¯åĵģ
    -0.07
     colo
    -0.07
    каÑĥ
    -0.07
     Lieu
    -0.07
    ÙĨس
    -0.07
    _ING
    -0.07
    haupt
    -0.07
    POSITIVE LOGITS
    haft
    0.06
    ado
    0.06
     fundra
    0.06
    .Flush
    0.06
    à¸ķระà¸ģูล
    0.06
    adera
    0.06
    åłĤ
    0.06
    éĻĦ带
    0.06
     propagated
    0.05
     Psychiat
    0.05
    Activations Density 0.019%

    No Known Activations