© 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. 19948
    Prev
    Next
    INDEX
    Explanations

    deterministic process or relation

    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
    人å±ħ
    -0.06
    éģIJ
    -0.06
    人为
    -0.06
    åѤ
    -0.05
    èĩªç«ĭ
    -0.05
    临åħ¶
    -0.05
    æ¦Ĥ
    -0.05
    auge
    -0.05
     expectations
    -0.05
    éĽĨä¸ŃçļĦ
    -0.05
    POSITIVE LOGITS
     deterministic
    0.06
    èµĦæĸĻ
    0.06
     foreseeable
    0.06
    èµĦæĸĻçļĦ
    0.06
     predictable
    0.06
     chained
    0.06
    chain
    0.05
     traced
    0.05
    追踪
    0.05
    è®°å½ķ
    0.05
    Activations Density 0.005%

    No Known Activations