© 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. 162645
    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¸Ĭæĸ¹
    -0.25
     pena
    -0.25
    大å°ı
    -0.24
    .setBorder
    -0.24
     Brace
    -0.24
    梯
    -0.24
    ä¸ĭæĸ¹
    -0.23
    IMA
    -0.23
    endant
    -0.23
    ([{
    -0.23
    POSITIVE LOGITS
    ãĥŀãĤ¤
    0.23
    çĻŀ
    0.23
    gi
    0.22
    -zone
    0.22
    vn
    0.22
    ãĤĭãĤĤãģ®
    0.22
    .shift
    0.22
    ÑĩÑĮ
    0.22
    ẳng
    0.22
    erp
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.