© 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. 18263
    Prev
    Next
    INDEX
    Explanations

    lists

    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
     acercar
    -0.06
    éļıåľ°
    -0.06
     mé
    -0.06
    ç¨ĭ
    -0.06
    éłĨ
    -0.06
    erings
    -0.05
    æīĵå¾Ĺ
    -0.05
     automatique
    -0.05
     matéri
    -0.05
    èļģ
    -0.05
    POSITIVE LOGITS
    ampa
    0.06
    illard
    0.06
    åı£çļĦ
    0.05
    eka
    0.05
    esz
    0.05
    çķĮå®ļ
    0.05
    quake
    0.05
    hun
    0.05
    zb
    0.05
    éŨçļĦ
    0.05
    Activations Density 0.001%

    No Known Activations