© 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. 18911
    Prev
    Next
    INDEX
    Explanations

    colon or period followed by sentence start

    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
     ë°©
    -0.05
    atica
    -0.05
    ÑĢÑı
    -0.05
     pl
    -0.05
    纤
    -0.05
     DET
    -0.05
    çIJĨ
    -0.05
     eg
    -0.05
     manip
    -0.05
     widely
    -0.05
    POSITIVE LOGITS
    placer
    0.06
    æĥ©
    0.06
    à¸Ĥวาà¸ĩ
    0.06
    Ñİз
    0.06
    kler
    0.06
    ÙĩÙĪد
    0.06
    ode
    0.06
    ruhe
    0.06
    resto
    0.06
    rau
    0.06
    Activations Density 0.004%

    No Known Activations