© 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. 20598
    Prev
    Next
    INDEX
    Explanations

    loved ones

    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
    ärten
    -0.06
    æīĢ以è¦ģ
    -0.06
    )set
    -0.06
    ordan
    -0.06
    ansas
    -0.06
    heber
    -0.05
    æĪĸçĶ±
    -0.05
    zeb
    -0.05
    Ñģловно
    -0.05
    werkt
    -0.05
    POSITIVE LOGITS
    éĺĻ
    0.07
    es
    0.06
    ë¡ľ
    0.06
    tes
    0.06
    liness
    0.06
    ora
    0.05
    esco
    0.05
    gro
    0.05
    gar
    0.05
    hun
    0.05
    Activations Density 0.003%

    No Known Activations