© 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. 20071
    Prev
    Next
    INDEX
    Explanations

    engagement and its outcomes

    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
    ation
    -0.07
    E
    -0.06
    å¾ĭ
    -0.06
    aller
    -0.05
    extr
    -0.05
    ide
    -0.05
    ATION
    -0.05
     “
    -0.05
     to
    -0.05
    bul
    -0.05
    POSITIVE LOGITS
    èĻı
    0.07
    çĶ¨çļĦ
    0.07
     diligence
    0.07
     sóc
    0.07
    cket
    0.06
    entiful
    0.06
     Grat
    0.06
     fabr
    0.06
    ãĤ¯ãĤ¿
    0.06
    igram
    0.06
    Activations Density 0.004%

    No Known Activations