© 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. 20851
    Prev
    Next
    INDEX
    Explanations

    population genetics and history

    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
     Morse
    -0.07
    odge
    -0.07
    oze
    -0.07
    меÑĤ
    -0.07
    rah
    -0.07
     Wolff
    -0.07
    .Excel
    -0.07
     solid
    -0.06
     Ge
    -0.06
    metic
    -0.06
    POSITIVE LOGITS
     lineage
    0.10
    糸
    0.09
    ALLE
    0.08
     models
    0.08
     ancestral
    0.08
     Theory
    0.08
     branching
    0.08
    åŁºåĽłç»Ħ
    0.08
     theory
    0.08
    itarian
    0.08
    Activations Density 0.028%

    No Known Activations