© 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. 38126
    Prev
    Next
    INDEX
    Explanations

    increasing or ascending sequences

    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
    æ±İ
    -0.08
    åĪĨä¸Ńå¿ĥ
    -0.08
    ugin
    -0.08
    REEN
    -0.08
    æ³Į
    -0.07
    allee
    -0.07
    .attrib
    -0.07
    á»Ļc
    -0.07
    öff
    -0.07
    çĤ¹æѤ
    -0.07
    POSITIVE LOGITS
    åºıåĪĹ
    0.11
     progression
    0.10
     consecutive
    0.10
     sequence
    0.09
    éĢĴå¢ŀ
    0.09
     sequences
    0.09
    紧绷
    0.09
     strict
    0.09
     Sequence
    0.08
     ascending
    0.08
    Activations Density 0.005%

    No Known Activations