© 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. 28893
    Prev
    Next
    INDEX
    Explanations

    action verbs before related nouns

    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
    大çİĭ
    -0.08
     ÐŁÑĢод
    -0.08
    issons
    -0.07
    éĺ³æĺ¥
    -0.07
     Anteil
    -0.07
     Pilk
    -0.07
    åĪĨ享åĪ°
    -0.07
    è²Ĥ
    -0.07
    éĢļè¿ĩåĪĨæŀIJ
    -0.07
    AWN
    -0.07
    POSITIVE LOGITS
    å®ŀéĻħ
    0.11
    å®ŀéĻħçļĦ
    0.10
     accordingly
    0.10
    缸åºĶçļĦ
    0.10
    å®ŀæĸ½
    0.10
     actual
    0.10
    æį®æѤ
    0.10
    缸åºĶ
    0.10
    actual
    0.10
    æī§è¡Į
    0.10
    Activations Density 0.291%

    No Known Activations