© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17297
    Prev
    Next
    INDEX
    Explanations

    building skills and training

    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
    ä¸įåıĬæĹ¶
    -0.08
    éĺ¿å¼¥éĻĢ
    -0.07
    fras
    -0.07
     crud
    -0.07
    angk
    -0.07
    åıĬæĹ¶çļĦ
    -0.07
    elon
    -0.06
    джÑĥ
    -0.06
    venu
    -0.06
    åıĬæĹ¶åIJij
    -0.06
    POSITIVE LOGITS
     rel
    0.06
    s
    0.05
     reform
    0.05
     functional
    0.05
     le
    0.05
     :
    0.05
    ↵
    0.05
    ellos
    0.05
     &
    0.05
     ne
    0.05
    Activations Density 0.011%

    No Known Activations