© 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. 43996
    Prev
    Next
    INDEX
    Explanations

    initial followed by API or scale

    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
    eter
    -0.09
    ovima
    -0.08
    esian
    -0.08
    age
    -0.08
    eters
    -0.08
    shops
    -0.08
    说æĺ¯
    -0.07
    onomic
    -0.07
    erei
    -0.07
    nasium
    -0.07
    POSITIVE LOGITS
    ities
    0.10
    OrDefault
    0.09
    ly
    0.09
    iza
    0.09
    aunch
    0.09
    mente
    0.08
    ividual
    0.08
    most
    0.08
    éłĥãģ®
    0.08
    ampton
    0.08
    Activations Density 0.031%

    No Known Activations