© 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. 5185
    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
     lÆ°u
    -0.29
     starred
    -0.29
    ä¼ģä¸ļåıijå±ķ
    -0.28
    askan
    -0.28
     backing
    -0.27
    åĵ¨
    -0.26
    认åIJĮ
    -0.25
     ÑĢаÑģпÑĢоÑģÑĤÑĢанен
    -0.24
    izard
    -0.24
    OUSE
    -0.23
    POSITIVE LOGITS
    odia
    0.29
    .AUTO
    0.26
    ()>↵
    0.24
    itto
    0.24
     maxSize
    0.24
    çĦļçĥ§
    0.24
     simult
    0.24
    åIJĮæŶ
    0.24
    åħ¨
    0.23
    elig
    0.23
    Activations Density 0.118%

    No Known Activations

    This feature has no known activations.