© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJİèĢħ
    -0.28
     polling
    -0.25
    两èĢħ
    -0.25
    mojom
    -0.25
     Austral
    -0.25
     observational
    -0.24
    横
    -0.24
     observation
    -0.24
     broadcasting
    -0.23
     Publishing
    -0.23
    POSITIVE LOGITS
    åĪ«
    0.28
    ê³ł
    0.28
    STRUCT
    0.26
    phin
    0.26
    lke
    0.26
    oins
    0.25
    å¾ģæ±Ĥ
    0.25
     Instructions
    0.25
    ptic
    0.25
    以为
    0.24
    Activations Density 1.951%

    No Known Activations

    This feature has no known activations.