© 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. 21766
    Prev
    Next
    INDEX
    Explanations

    web.xml context-param

    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
    agen
    -0.07
    orf
    -0.06
     >&
    -0.06
    åı¶è½®
    -0.06
    aliz
    -0.06
    vist
    -0.06
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    -0.06
    cart
    -0.06
    abilit
    -0.06
    åĩºåİ»äºĨ
    -0.06
    POSITIVE LOGITS
    uppy
    0.06
    öffentlichen
    0.05
    ighting
    0.05
    ushima
    0.05
    /dom
    0.05
    æ±łä¸Ń
    0.05
    æĪ®
    0.05
     Titan
    0.05
    ihi
    0.05
    _assert
    0.05
    Activations Density 0.001%

    No Known Activations