© 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. 31-TRANSCODER-HP
    7. 19535
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤıãĤĬ
    -0.27
    liness
    -0.26
    sup
    -0.25
    ac
    -0.25
     Newly
    -0.24
    æĪIJ
    -0.24
    hoa
    -0.24
    ìĦ±
    -0.24
     sc
    -0.24
     ac
    -0.23
    POSITIVE LOGITS
    nts
    0.29
    nda
    0.28
    奢ä¾Ī
    0.27
    ntax
    0.26
    åħijçİ°
    0.26
    ptom
    0.26
    èĨĽ
    0.26
    ble
    0.26
    sterol
    0.25
    DataRow
    0.25
    Activations Density 0.004%

    No Known Activations