© 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. 19007
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags or structure

    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
    é«ĺè´¨éĩıçļĦ
    -0.05
    faktor
    -0.05
    o
    -0.05
    izie
    -0.05
     Bal
    -0.05
     hạ
    -0.05
    arser
    -0.05
     Sir
    -0.05
     Avr
    -0.05
    ruck
    -0.05
    POSITIVE LOGITS
    imer
    0.07
    åľ°åĮº
    0.06
    apult
    0.06
    alj
    0.06
    à¸ģัà¸Ļà¹Ģลย
    0.06
    uia
    0.06
    éĮ¬
    0.06
     ìĺĪë¹Ħ
    0.05
    åĬ¡
    0.05
     Lone
    0.05
    Activations Density 0.001%

    No Known Activations