© 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. 64031
    Prev
    Next
    INDEX
    Explanations

    Rodriguez or NOP

    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
    occhio
    -0.08
    Infos
    -0.08
    سر
    -0.07
    scopy
    -0.07
    forme
    -0.07
    è¡·
    -0.07
    å®ĥ以
    -0.07
    esson
    -0.07
    æĪij以
    -0.07
    ItemClick
    -0.07
    POSITIVE LOGITS
    éĽĢ
    0.07
    erp
    0.07
    å°ģ
    0.06
    ran
    0.06
    尼奥
    0.06
    æī§è¡Į人
    0.06
    usting
    0.06
    izers
    0.06
    飬
    0.06
     border
    0.06
    Activations Density 0.006%

    No Known Activations