© 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. 7998
    Prev
    Next
    INDEX
    Explanations

    portfolio

    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
    ç½®
    -0.25
     creeping
    -0.24
    NavController
    -0.24
     llev
    -0.23
    tram
    -0.23
    Wind
    -0.23
    leo
    -0.22
    wind
    -0.22
    dez
    -0.22
    _wind
    -0.22
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.31
    izen
    0.29
    GRAM
    0.26
    -wide
    0.26
    æľīå¤ļ大
    0.26
    /package
    0.25
     sack
    0.24
     litter
    0.24
    श
    0.24
    .Queue
    0.24
    Activations Density 0.690%

    No Known Activations