© 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. 7511
    Prev
    Next
    INDEX
    Explanations

    Looking and people

    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
    OMPI
    -0.29
    è´¹çİĩ
    -0.26
     minHeight
    -0.25
    åıĹå½±åĵį
    -0.25
    vig
    -0.25
     tá»
    -0.25
    sheets
    -0.25
    çģı
    -0.25
    owi
    -0.24
    .getMin
    -0.24
    POSITIVE LOGITS
     half
    0.31
    å®ļ
    0.28
    åįĬ
    0.28
    Half
    0.25
    æĭ±
    0.25
     convex
    0.25
    _half
    0.25
    issor
    0.25
     Husband
    0.24
    转åŀĭ
    0.24
    Activations Density 0.029%

    No Known Activations