© 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. 22167
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¦ĤçĥŁ
    -0.06
    ä¼ļé¦Ĩ
    -0.05
     lancar
    -0.05
    ãĤīãģı
    -0.05
     keyword
    -0.05
    ilen
    -0.05
    ttp
    -0.05
     shed
    -0.05
    žu
    -0.05
    çī¹çĤ¹æĺ¯
    -0.05
    POSITIVE LOGITS
    withstanding
    0.07
    vals
    0.06
    tons
    0.06
    Ñįм
    0.06
    éĺ»
    0.05
    人士
    0.05
    ÙĪاÙĦ
    0.05
    lags
    0.05
    .Distance
    0.05
    à¸ŀึà¸ĩ
    0.05
    Activations Density 0.000%

    No Known Activations