© 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. 14-TRANSCODER-HP
    7. 40087
    Prev
    Next
    INDEX
    Explanations

    stress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é£İ鼨
    -0.29
    eca
    -0.26
    ::-
    -0.26
    Äĥr
    -0.24
    zs
    -0.24
    -anchor
    -0.24
    ilk
    -0.24
    身为
    -0.23
    æĶ¾æĺł
    -0.23
    Cream
    -0.23
    POSITIVE LOGITS
     adul
    0.27
    æ¶Īæŀģ
    0.26
    åłķ
    0.25
     volont
    0.25
    æµģåĬ¨æĢ§
    0.25
     saldo
    0.24
    å¼¥
    0.24
    __).
    0.24
     idi
    0.24
    fin
    0.23
    Activations Density 0.181%

    No Known Activations