© 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. 142243
    Prev
    Next
    INDEX
    Explanations

    Technical/Academic document snippets

    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
    为ä¹ĭ
    -0.33
     keyed
    -0.28
     magician
    -0.28
    èĻº
    -0.27
    rish
    -0.26
     muster
    -0.26
     ordinarily
    -0.25
    ä¸ĢåįĬ
    -0.24
    IMENT
    -0.24
    ément
    -0.24
    POSITIVE LOGITS
    counts
    0.31
     counts
    0.28
    _counts
    0.26
    临
    0.26
     COUNT
    0.25
    nbr
    0.25
     mic
    0.25
    (other
    0.24
    icts
    0.24
    ounc
    0.24
    Activations Density 16.406%

    No Known Activations