© 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. 7649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    processor
    -0.27
    ivas
    -0.27
     pride
    -0.26
    çĦī
    -0.26
     behaviours
    -0.25
    bio
    -0.24
    æĮĩ
    -0.24
    bih
    -0.24
    é«ĺå°Ķ
    -0.24
     vibr
    -0.24
    POSITIVE LOGITS
    aos
    0.27
    ebra
    0.25
    serrat
    0.25
    åIJįé¢Ŀ
    0.25
    trand
    0.24
     camper
    0.23
    een
    0.23
     spotlight
    0.23
     ND
    0.23
    <=$
    0.23
    Activations Density 0.127%

    No Known Activations

    This feature has no known activations.