© 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. 28962
    Prev
    Next
    INDEX
    Explanations

    -ology / -ological suffixes

    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
    acular
    -0.09
    oir
    -0.09
    igung
    -0.09
    Åijl
    -0.09
    aneous
    -0.08
    iente
    -0.08
     lunak
    -0.08
    arial
    -0.08
    leigh
    -0.08
    orial
    -0.08
    POSITIVE LOGITS
    raphic
    0.09
    åŃ¦å®¶
    0.09
    agues
    0.08
    gia
    0.08
    emma
    0.08
    ypse
    0.08
    ically
    0.08
    athering
    0.08
    jmp
    0.08
    /ge
    0.08
    Activations Density 0.097%

    No Known Activations