© 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. 62888
    Prev
    Next
    INDEX
    Explanations

    company names or types

    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
    .pm
    -0.07
     Norsk
    -0.07
    .gov
    -0.07
    饶
    -0.07
    .wikipedia
    -0.07
    åij¼
    -0.06
    çĺ
    -0.06
    ç¨įæľī
    -0.06
    urn
    -0.06
    念
    -0.06
    POSITIVE LOGITS
     Ltd
    0.09
    ฯ
    0.09
    åıĬ个人
    0.08
    äºijé£ŀ
    0.08
    ervices
    0.08
    รส
    0.08
     Pvt
    0.07
    xea
    0.07
    metics
    0.07
    好åŃ©åŃIJ
    0.07
    Activations Density 0.579%

    No Known Activations