© 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. 24-TRANSCODER-HP
    7. 150931
    Prev
    Next
    INDEX
    Explanations

    End of sentence punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃc
    -0.30
     early
    -0.25
     circuit
    -0.25
    eroon
    -0.25
    &#
    -0.24
     negot
    -0.24
     Early
    -0.24
    midd
    -0.23
    æıIJæĹ©
    -0.23
     detect
    -0.23
    POSITIVE LOGITS
    åIJĦæĸ¹éĿ¢
    0.30
    说çļĦæĺ¯
    0.29
    [assembly
    0.26
    æĮĩå®ļ
    0.26
    [](
    0.25
     allegiance
    0.24
    (pop
    0.24
    waves
    0.24
    ))/(
    0.23
    éĶŃ
    0.23
    Activations Density 0.114%

    No Known Activations