© 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. 20074
    Prev
    Next
    INDEX
    Explanations

    press after selecting or choosing

    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
    ç»Ŀ
    -0.05
    get
    -0.05
    /
    -0.05
    af
    -0.05
    3
    -0.05
    æīĢåľ¨
    -0.05
    /{
    -0.05
    æİ¥åıĹ
    -0.05
     whole
    -0.05
    éĢı
    -0.04
    POSITIVE LOGITS
    aktu
    0.07
    føl
    0.07
     arty
    0.06
    anjutkan
    0.06
    çIJĥåľº
    0.06
    azah
    0.06
    enea
    0.06
    жиÑĤе
    0.06
    ernen
    0.06
     lév
    0.06
    Activations Density 0.004%

    No Known Activations