© 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. 5994
    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
    .norm
    -0.27
    aya
    -0.26
     audience
    -0.26
    Ãľ
    -0.26
    ip
    -0.26
    Us
    -0.25
    ipt
    -0.25
    ullet
    -0.24
    ~-
    -0.24
     es
    -0.24
    POSITIVE LOGITS
    AuthProvider
    0.26
    è¿ĺä¸įå¦Ĥ
    0.26
    zÅij
    0.25
     burst
    0.25
     Observable
    0.25
    dür
    0.25
     explos
    0.24
    åİ©
    0.24
    uai
    0.23
    oggle
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.