© 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. 23-TRANSCODER-HP
    7. 161699
    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
    æģ¸
    -0.28
    è¦ģ说
    -0.28
     Ground
    -0.25
    RM
    -0.25
    dice
    -0.25
     Surprise
    -0.25
     RM
    -0.24
    quires
    -0.24
     ON
    -0.24
    grounds
    -0.24
    POSITIVE LOGITS
    æĻ®
    0.30
    illin
    0.28
     render
    0.27
    OAD
    0.27
    æĪIJçĨŁçļĦ
    0.27
    为ä¸ŃåĽ½
    0.26
    ension
    0.26
    enu
    0.26
    ighted
    0.25
    etine
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.