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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5446
    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
    ç®ķ
    -0.29
    æľŁ
    -0.26
     iT
    -0.26
    entic
    -0.26
    inals
    -0.25
    骸
    -0.25
    ié
    -0.25
    empl
    -0.25
     borr
    -0.25
    pedia
    -0.24
    POSITIVE LOGITS
    acje
    0.27
     registry
    0.26
    )init
    0.25
    æĹ¢æľī
    0.25
    ady
    0.25
    rift
    0.24
    abee
    0.24
    RITE
    0.24
    atatype
    0.24
    adesh
    0.24
    Activations Density 1.579%

    No Known Activations

    This feature has no known activations.