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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23874
    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
    è¹²
    -0.32
    oling
    -0.27
    asi
    -0.27
     scaling
    -0.26
    oundation
    -0.26
    posting
    -0.24
     Carpet
    -0.24
    sit
    -0.24
    ulate
    -0.24
    çĶ¨æĪ·æıIJä¾Ľ
    -0.24
    POSITIVE LOGITS
    é»ijçĻ½
    0.26
    Vers
    0.26
    (layers
    0.26
    Nich
    0.25
    顶å±Ĥ
    0.24
     NOI
    0.24
    çļĦéĤ£ä¸Ģ
    0.23
    isex
    0.23
     Со
    0.23
    dale
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.