© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20076
    Prev
    Next
    INDEX
    Explanations

    warning or concern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çªģ
    -0.07
    pz
    -0.06
    å¦ŀ
    -0.06
    pite
    -0.06
    angk
    -0.06
    ément
    -0.06
    èĮ¹
    -0.05
    emez
    -0.05
    -ext
    -0.05
    Ùħد
    -0.05
    POSITIVE LOGITS
     harmless
    0.07
     Concern
    0.06
     concern
    0.06
    ä»ĭæĦı
    0.06
    .warn
    0.06
     concerning
    0.05
    æģ¼
    0.05
     impunity
    0.05
     Warn
    0.05
     minor
    0.05
    Activations Density 0.118%

    No Known Activations