© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ctors
    -0.26
    oped
    -0.25
     kut
    -0.24
     sponge
    -0.24
    ción
    -0.24
     heav
    -0.24
    uteur
    -0.23
    aminer
    -0.23
    å¿«æīĭ
    -0.23
     capsules
    -0.23
    POSITIVE LOGITS
    è¿ľ
    0.30
    åĽłä¸ºæĪij们
    0.27
     fr
    0.26
    zÄħ
    0.26
    -axis
    0.25
     xu
    0.25
    Far
    0.24
     sin
    0.23
    åĽłä¸º
    0.23
    outs
    0.23
    Activations Density 0.001%

    No Known Activations