© 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. 7069
    Prev
    Next
    INDEX
    Explanations

    Everything

    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
    说è¿ĩ
    -0.30
     prefix
    -0.28
    Prefix
    -0.26
    breaking
    -0.25
    _prefix
    -0.25
     prefixes
    -0.24
     Uncategorized
    -0.24
     Prefix
    -0.24
    prefix
    -0.24
    shopping
    -0.24
    POSITIVE LOGITS
    cae
    0.31
    lates
    0.27
    è§ĩ
    0.27
    æĸ¹æ¡Ī
    0.25
    ä¸įåı¯éģ¿åħį
    0.24
    _Manager
    0.24
     hj
    0.24
    (dot
    0.23
     sout
    0.23
     synerg
    0.23
    Activations Density 0.017%

    No Known Activations