© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39389
    Prev
    Next
    INDEX
    Explanations

    say "expect" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expected
    -1.15
     Expected
    -1.13
    expected
    -1.06
    Expected
    -1.05
     expect
    -0.98
     expectations
    -0.97
    (expected
    -0.96
    é¢ĦæľŁ
    -0.96
     Expect
    -0.95
     expectation
    -0.92
    POSITIVE LOGITS
     intensely
    0.30
    就被
    0.29
    ulously
    0.29
     uncomfort
    0.29
    ä¹Łè®¸æĺ¯
    0.29
    taÅŁ
    0.29
     legitimately
    0.29
    èĢĮçİ°åľ¨
    0.29
     irresist
    0.28
     intox
    0.28
    Activations Density 17.934%

    No Known Activations