© 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. 63682
    Prev
    Next
    INDEX
    Explanations

    positive descriptive adjectives

    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
    ä¸įåĪ©
    -0.08
    ä¸į好äºĨ
    -0.08
     famously
    -0.08
    iglia
    -0.07
    anggung
    -0.07
    åī§çĥĪ
    -0.07
    åī§çĥĪçļĦ
    -0.07
    ÏĦί
    -0.07
    atakan
    -0.07
    quist
    -0.07
    POSITIVE LOGITS
     overall
    0.09
    å¾Īæľī
    0.08
     excellent
    0.08
     underrated
    0.08
    åѦåĪ°äºĨ
    0.07
    ä¸įæĦ§æĺ¯
    0.07
    Overall
    0.07
    çī¹åĪ«æĺ¯
    0.07
     informative
    0.07
     compliment
    0.07
    Activations Density 0.772%

    No Known Activations