© 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. 20-TRANSCODER-HP
    7. 107789
    Prev
    Next
    INDEX
    Explanations

    Sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lap
    -0.31
    æĿ¡
    -0.27
    çİĭçīĮ
    -0.26
    ستاÙĨ
    -0.25
    ones
    -0.25
    诸
    -0.25
    ä¿ĥ
    -0.25
    æĹ¶æľŁçļĦ
    -0.24
    åħ¹
    -0.24
    è§Ĥä¼Ĺ
    -0.24
    POSITIVE LOGITS
    ĶĦ
    0.30
    ain
    0.30
    tribute
    0.28
     store
    0.27
    .Expressions
    0.26
     stored
    0.26
    dress
    0.25
    thon
    0.25
     STORE
    0.25
    angen
    0.25
    Activations Density 45.487%

    No Known Activations