© 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. 18-TRANSCODER-HP
    7. 89203
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohl
    -0.29
     electrons
    -0.28
    è°
    -0.28
    åİŁåŃIJ
    -0.27
     atoms
    -0.27
    åĽº
    -0.26
    .nextToken
    -0.25
     compound
    -0.25
     electron
    -0.25
    æľī个
    -0.25
    POSITIVE LOGITS
    etwork
    0.27
    éĵ±
    0.26
    OnChange
    0.24
    onné
    0.24
    Duplicates
    0.24
    emons
    0.24
    åĪ·
    0.24
     Judiciary
    0.24
     OnInit
    0.23
     Already
    0.23
    Activations Density 32.816%

    No Known Activations