© 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. 23-TRANSCODER-HP
    7. 163360
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įæİĴéĻ¤
    -0.30
    isol
    -0.28
    isl
    -0.26
    istribution
    -0.25
     isolated
    -0.24
    assy
    -0.24
     punched
    -0.24
    æĦıä¹īä¸ĬçļĦ
    -0.24
     miss
    -0.24
     ahead
    -0.24
    POSITIVE LOGITS
     Venture
    0.28
    身åIJİ
    0.27
    åħīçĶµ
    0.25
    å°±æĺ¯åĽłä¸º
    0.25
    brace
    0.24
    .pose
    0.24
    稽
    0.24
    大åºĨ
    0.23
    -clear
    0.23
    chter
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.