© 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. 5369
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
     fast
    -0.28
    åºĨ幸
    -0.27
     call
    -0.27
     staring
    -0.26
    /fast
    -0.25
    sing
    -0.25
    èIJ¥è¿IJ
    -0.25
    -fast
    -0.25
     addition
    -0.24
     calling
    -0.24
    POSITIVE LOGITS
    饶
    0.31
     Boots
    0.27
    èĩ³å°ij
    0.25
    idel
    0.25
     Illustrated
    0.25
    çļĦçĶ·äºº
    0.25
    repos
    0.25
    çħ¨
    0.24
    åĬ¨äºº
    0.24
    PLICIT
    0.24
    Activations Density 0.006%

    No Known Activations