© 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. 20417
    Prev
    Next
    INDEX
    Explanations

    social + domains (news, gaming, science, interaction, insects)

    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
    ADING
    -0.09
    rtle
    -0.08
     sedu
    -0.08
    ëģĿ
    -0.08
    FINITY
    -0.08
    ãģĹãĤĤ
    -0.07
    ÙĤس
    -0.07
     sequer
    -0.07
     chô
    -0.07
    essel
    -0.07
    POSITIVE LOGITS
    izing
    0.10
    s
    0.10
    ized
    0.09
    ization
    0.08
     minded
    0.08
    ize
    0.08
    isation
    0.08
    -minded
    0.08
    åŃ¦å®¶
    0.07
    mente
    0.07
    Activations Density 0.050%

    No Known Activations