© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19692
    Prev
    Next
    INDEX
    Explanations

    <? PHP XML HTML tags

    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
    اÙħØ©
    -0.06
    wak
    -0.05
    VD
    -0.05
    geb
    -0.05
    ann
    -0.05
    cc
    -0.05
    交
    -0.04
    ffit
    -0.04
    clare
    -0.04
    elly
    -0.04
    POSITIVE LOGITS
    sequent
    0.06
    æĦ
    0.06
    rias
    0.06
     industriali
    0.05
    zus
    0.05
    stit
    0.05
    并æıIJ交
    0.05
    онов
    0.05
    ÙĦاÙĤ
    0.05
    ancier
    0.05
    Activations Density 0.180%

    No Known Activations