© 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. 21655
    Prev
    Next
    INDEX
    Explanations

    systemreportDLL(domaindemoforms/admin

    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
    гÑĢ
    -0.05
    bull
    -0.05
    à¹īà¸Ļ
    -0.05
    ouns
    -0.05
    çı
    -0.05
    umus
    -0.05
    eness
    -0.05
    åħ¨
    -0.05
    ilai
    -0.05
    ország
    -0.05
    POSITIVE LOGITS
    åĪĨä¼ļ
    0.07
     tr
    0.06
    uffle
    0.06
    åľ©
    0.06
    aver
    0.06
    ãģ³
    0.05
     nut
    0.05
     ber
    0.05
     komplette
    0.05
     caster
    0.05
    Activations Density 0.003%

    No Known Activations