© 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. 18140
    Prev
    Next
    INDEX
    Explanations

    bowl of

    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
    糸
    -0.06
    edenk
    -0.06
    илÑĮ
    -0.06
    åİ¢
    -0.06
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    -0.06
    ила
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    à¸ķัว
    -0.06
    umper
    -0.06
    ĺ
    -0.05
    POSITIVE LOGITS
    atter
    0.07
     McG
    0.06
    ful
    0.05
    ATYPE
    0.05
     Nẵng
    0.05
     bowl
    0.05
    èĻŀ
    0.05
    ide
    0.05
    çĥ
    0.05
    ãĤ¦ãĤ§ãĤ¢
    0.05
    Activations Density 0.006%

    No Known Activations