© 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. 32-TRANSCODER-HP
    7. 42024
    Prev
    Next
    INDEX
    Explanations

    unusual text/code sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stash
    -0.30
    esan
    -0.28
    zers
    -0.27
    zon
    -0.27
    stk
    -0.27
    st
    -0.26
     Bapt
    -0.26
    桶
    -0.25
     prospect
    -0.25
    vant
    -0.25
    POSITIVE LOGITS
    ylv
    0.27
    né
    0.26
    tep
    0.25
    .lu
    0.25
    ëłµ
    0.24
    ertia
    0.23
    å½Ī
    0.23
    NP
    0.23
    nings
    0.23
     trade
    0.23
    Activations Density 0.001%

    No Known Activations