© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    threshold, phase, rate, intensity

    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
    endir
    -0.07
     suj
    -0.07
    ÅĽc
    -0.07
    edik
    -0.07
    amus
    -0.07
    ç·ł
    -0.07
    å¸Ŀéĥ½
    -0.07
    iket
    -0.07
     Capitals
    -0.06
    Capital
    -0.06
    POSITIVE LOGITS
    对åºĶ
    0.10
    临çķĮ
    0.09
     corresponding
    0.09
    对åºĶçļĦ
    0.09
     Correspond
    0.08
     corresponds
    0.08
    å°įæĩī
    0.08
    éĺĪåĢ¼
    0.08
     corrispond
    0.08
     threshold
    0.07
    Activations Density 0.032%

    No Known Activations