© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21305
    Prev
    Next
    INDEX
    Explanations

    domain extensions or suffixes

    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
    ansom
    -0.07
    mena
    -0.07
    indel
    -0.07
    fter
    -0.06
    æĵº
    -0.06
    æijĨåĬ¨
    -0.06
    Beh
    -0.06
    odaw
    -0.06
    enga
    -0.06
    ahun
    -0.06
    POSITIVE LOGITS
     imp
    0.06
    Ùī
    0.05
    èĤł
    0.05
     scor
    0.05
    缺
    0.05
    åĪĻ为
    0.05
    ä¹³
    0.05
    ä¸į好æĦıæĢĿ
    0.05
    æĿĢ
    0.04
    ä¹ł
    0.04
    Activations Density 0.319%

    No Known Activations