© 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. 19-TRANSCODER-HP
    7. 7718
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    è¿ĩ渡
    -0.30
    croft
    -0.27
    ä¿®çIJĨ
    -0.27
    ä»Ĺ
    -0.27
    chner
    -0.27
    cles
    -0.26
    çŀ¬
    -0.25
    ðŁĺĺ
    -0.24
    lesh
    -0.23
    icrosoft
    -0.23
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.26
    äºĨèµ·æĿ¥
    0.26
    xfff
    0.25
    å¸ĮæľĽèĥ½å¤Ł
    0.25
    inic
    0.24
     represent
    0.24
    ivism
    0.24
                                    ↵
    0.23
     buckets
    0.23
    ullan
    0.23
    Activations Density 0.068%

    No Known Activations