© 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. 19748
    Prev
    Next
    INDEX
    Explanations

    session.startOAuth2Authentication

    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
    ikk
    -0.06
    Sorting
    -0.05
    ât
    -0.05
     Region
    -0.05
     Fl
    -0.05
    ίκη
    -0.05
     Deep
    -0.05
    tat
    -0.05
    éta
    -0.05
    witz
    -0.05
    POSITIVE LOGITS
    quals
    0.05
    pos
    0.05
    edom
    0.05
    å¾ĵ
    0.05
    åľ¨åĨħ
    0.05
    æĵŀ
    0.05
     внеÑĪниÑħ
    0.05
    undial
    0.05
    åĥıæĪij
    0.05
    æĬĬè¿Ļ
    0.05
    Activations Density 0.001%

    No Known Activations