© 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. 21580
    Prev
    Next
    INDEX
    Explanations

    robustness, modification, attack, optimization

    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
    ague
    -0.06
    fer
    -0.06
    åħ¼
    -0.06
     Ñĥп
    -0.05
    ÙĤØ·
    -0.05
    ferenz
    -0.05
    clipse
    -0.05
     scrap
    -0.05
    hook
    -0.05
    eller
    -0.05
    POSITIVE LOGITS
    estä
    0.07
    åľ¨æĹģè¾¹
    0.06
     alrededores
    0.06
    brit
    0.06
    asih
    0.06
     alentours
    0.06
    çĤ¹åIJİ
    0.06
    edian
    0.06
    endom
    0.06
    Modified
    0.06
    Activations Density 0.002%

    No Known Activations