© 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. 46831
    Prev
    Next
    INDEX
    Explanations

    Court document titles and references

    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
     Jarvis
    -0.07
    ä¹Łè¯¥
    -0.07
    üz
    -0.06
    üns
    -0.06
    oin
    -0.06
    à¹Ģรีย
    -0.06
    ç³»çļĦ
    -0.06
     Weinstein
    -0.06
    Independ
    -0.06
    viron
    -0.06
    POSITIVE LOGITS
    ÙĦÙĪد
    0.08
    WithValue
    0.08
    çķĶ
    0.08
    edal
    0.08
    æĻĵ举
    0.07
    åĵĪæĭī
    0.07
    çĪ±æĪij
    0.07
    åħĭåĬĽ
    0.07
    ç°¿
    0.07
    å¤ļ款
    0.07
    Activations Density 0.002%

    No Known Activations