© 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. 20963
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values

    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
    roma
    -0.07
     Ordin
    -0.06
    å³
    -0.06
    icated
    -0.06
    poste
    -0.06
    iante
    -0.06
    åIJ¦
    -0.05
    omb
    -0.05
    æĹ¥å¸¸çĶŁæ´»
    -0.05
    fv
    -0.05
    POSITIVE LOGITS
    еÑģÑĤи
    0.06
    顾
    0.05
    rac
    0.05
    ÙĪرÙĩا
    0.05
    åĶ®
    0.05
    opal
    0.05
    vola
    0.05
    åĨĮ
    0.05
    heden
    0.05
    -path
    0.05
    Activations Density 0.001%

    No Known Activations