© 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. 17001
    Prev
    Next
    INDEX
    Explanations

    function or method calls

    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
    çĥĪ
    -0.06
    ä¸Ģéģĵ
    -0.05
    gable
    -0.05
    é«ĺè´¨éĩı
    -0.05
    å®ļçļĦ
    -0.05
    åij½åIJįçļĦ
    -0.05
    åĽŀçŃĶéĹ®é¢ĺ
    -0.05
    æ¯ĶåĪ©
    -0.05
    åij½åIJį
    -0.05
    çķĮ
    -0.05
    POSITIVE LOGITS
    inh
    0.07
    ä¸ŃéĢļ
    0.06
    inson
    0.06
    alum
    0.06
    entered
    0.06
    igno
    0.06
    çIJĽ
    0.06
    unlink
    0.06
    rÃŃan
    0.05
    è¦ģ为
    0.05
    Activations Density 0.031%

    No Known Activations