© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5043
    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
     Psr
    -0.27
    ebb
    -0.26
    zza
    -0.25
     ++↵
    -0.25
    æīĴ
    -0.25
     cages
    -0.24
    碰æĴŀ
    -0.24
    å¼łåħĪçĶŁ
    -0.24
    zzarella
    -0.24
     hoop
    -0.24
    POSITIVE LOGITS
     flipping
    0.28
    RY
    0.26
    .handleChange
    0.25
    ocyte
    0.25
    (Dense
    0.25
    ól
    0.24
    ä¸įåĨį
    0.24
     indeed
    0.24
    UIApplicationDelegate
    0.24
    _constructor
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.