© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7087
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itel
    -0.28
    nar
    -0.26
    pret
    -0.26
    tol
    -0.26
    å·¥ç¨ĭé¡¹çĽ®
    -0.25
     Sil
    -0.24
     python
    -0.24
     Version
    -0.24
    n
    -0.24
    身
    -0.24
    POSITIVE LOGITS
    æĦı大
    0.26
    .Registry
    0.26
     uniqueness
    0.25
    yssey
    0.25
    ourse
    0.25
     Beet
    0.24
    .ToolStrip
    0.24
    OwnerId
    0.24
    sono
    0.24
    OrFail
    0.23
    Activations Density 0.001%

    No Known Activations