© 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. 18366
    Prev
    Next
    INDEX
    Explanations

    using or following certain tokens

    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
    affected
    -0.06
    forme
    -0.05
    roe
    -0.05
    angk
    -0.05
     Bast
    -0.05
    roph
    -0.05
    ÑĸÑĢ
    -0.05
    沧海
    -0.05
    ×ķרת
    -0.05
    ×ķר×ķת
    -0.05
    POSITIVE LOGITS
    ub
    0.06
    วà¸Ļ
    0.06
    nEnter
    0.06
    ä¸įè¨Ģ
    0.06
    ian
    0.05
    elv
    0.05
    umo
    0.05
    éĩıèĥ½
    0.05
    è¯Ŀ
    0.05
    åĿŀ
    0.05
    Activations Density 0.001%

    No Known Activations