© 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. 33-TRANSCODER-HP
    7. 54299
    Prev
    Next
    INDEX
    Explanations

    say "re" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esar
    -0.29
    ész
    -0.29
     Roe
    -0.28
    argin
    -0.28
     sez
    -0.27
    -controls
    -0.27
    emics
    -0.26
    æĦıæĢĿ
    -0.26
    temps
    -0.26
    Ùħار
    -0.25
    POSITIVE LOGITS
    res
    0.76
    re
    0.63
     res
    0.61
    RES
    0.56
    reh
    0.54
    rep
    0.52
    	res
    0.52
    [res
    0.52
    RE
    0.51
    (res
    0.51
    Activations Density 0.015%

    No Known Activations