© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19043
    Prev
    Next
    INDEX
    Explanations

    address suffixes

    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
    ilde
    -0.05
    ä¸įæĶ¯æĮģ
    -0.05
    \v
    -0.05
    etat
    -0.05
    isin
    -0.05
     handic
    -0.05
    éĢłèĪ¹
    -0.05
     vô
    -0.05
    ä¸į带
    -0.05
     let
    -0.05
    POSITIVE LOGITS
    fol
    0.07
    ÙĪاÙĦ
    0.07
    åĪ©çļĦ
    0.06
    cas
    0.06
    æŃ¹
    0.06
    corp
    0.06
    miner
    0.06
    宿
    0.06
    cba
    0.06
    åªĽåªĽ
    0.06
    Activations Density 0.009%

    No Known Activations