© 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. 7486
    Prev
    Next
    INDEX
    Explanations

    Code and sequences

    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
     union
    -0.33
    union
    -0.31
    tÃł
    -0.30
    czy
    -0.29
    .tc
    -0.28
    -être
    -0.27
    è¿ĺåĮħæĭ¬
    -0.26
    cents
    -0.26
    etti
    -0.26
    pire
    -0.26
    POSITIVE LOGITS
    atem
    0.28
    nger
    0.27
    åı£
    0.27
    (mat
    0.26
    MAT
    0.25
     richer
    0.24
    æĻĴ
    0.24
    æ¨Ĺ
    0.24
    ç¡Ĵ
    0.23
    .setBackground
    0.23
    Activations Density 0.129%

    No Known Activations