© 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. 19029
    Prev
    Next
    INDEX
    Explanations

    modeldatabase models apis

    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
     defaults
    -0.06
     anyways
    -0.06
    κÏħ
    -0.05
    å·²åľ¨
    -0.05
    è´¸
    -0.05
     unsure
    -0.05
    lng
    -0.05
     ÙħØ«
    -0.05
    (),"
    -0.05
    odar
    -0.05
    POSITIVE LOGITS
    embro
    0.06
    variably
    0.06
    aan
    0.06
    eter
    0.06
    hammer
    0.05
    大æĦı
    0.05
    åĪ©
    0.05
    lessly
    0.05
    unda
    0.05
    루
    0.05
    Activations Density 0.003%

    No Known Activations