© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    Describes movement/processes

    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
    indi
    -0.28
    Æ°a
    -0.26
    egov
    -0.26
    маг
    -0.25
    èĬ±çĵ£
    -0.25
    个æĢ§åĮĸ
    -0.25
    羶
    -0.25
    çĶŁæķĪ
    -0.24
    ä¸įæŃ¢
    -0.24
    ito
    -0.24
    POSITIVE LOGITS
     rall
    0.26
    棱
    0.24
     mouth
    0.24
    NegativeButton
    0.24
    gages
    0.24
    eft
    0.24
    ólica
    0.23
    cÃŃ
    0.23
    ä»İå°ıå°±
    0.23
    Mounted
    0.23
    Activations Density 0.034%

    No Known Activations