© 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. 21734
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    åħ¨æĸ°çļĦ
    -0.07
    /Foundation
    -0.07
     tyt
    -0.07
    -writing
    -0.07
    OTTO
    -0.07
     ingred
    -0.06
    (er
    -0.06
    à¸Ĺรà¸ĩ
    -0.06
    qid
    -0.06
    коваÑĤÑĮ
    -0.06
    POSITIVE LOGITS
    L
    0.06
    G
    0.05
     L
    0.05
    omor
    0.05
    c
    0.05
    éĻĭ
    0.05
    g
    0.05
    per
    0.05
    constexpr
    0.05
     G
    0.04
    Activations Density 0.002%

    No Known Activations