© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    other

    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
    iras
    -0.29
    PTY
    -0.29
     RCS
    -0.28
    åĽłä¸ºæĪij们
    -0.26
     rumours
    -0.26
    xdb
    -0.26
     Lanka
    -0.25
    abcdef
    -0.24
    窣
    -0.24
     supervise
    -0.24
    POSITIVE LOGITS
    opro
    0.30
     every
    0.28
    ast
    0.27
    (next
    0.26
    å¸Ĥæ°ij
    0.26
     each
    0.26
    æIJ¬
    0.26
    GP
    0.26
     majority
    0.25
    .SaveChanges
    0.25
    Activations Density 0.255%

    No Known Activations