© 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. 53183
    Prev
    Next
    INDEX
    Explanations

    say "is"

    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
    wal
    -0.31
    æĹłåı¯
    -0.29
    iom
    -0.28
    äºı
    -0.26
    Por
    -0.25
    lion
    -0.24
    ×ķ×ĵ×Ķ
    -0.24
    playing
    -0.24
     por
    -0.24
     Lodge
    -0.24
    POSITIVE LOGITS
    .is
    0.46
    æĺ¯
    0.46
     is
    0.44
     lÃł
    0.43
    is
    0.42
    Is
    0.41
    -is
    0.40
     Is
    0.39
    _is
    0.37
     æĺ¯
    0.37
    Activations Density 0.111%

    No Known Activations