© 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. 162003
    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
    elight
    -0.28
    åħ¥çĿ¡
    -0.27
    å±ĢéĿ¢
    -0.27
    ully
    -0.27
     Lightning
    -0.25
    olis
    -0.25
    轨
    -0.25
    олод
    -0.24
    eer
    -0.24
    sleep
    -0.23
    POSITIVE LOGITS
    akes
    0.25
    è´
    0.25
    avad
    0.25
    åĽ½å®¶æĪĺçķ¥
    0.25
     release
    0.25
    è´´åIJ§
    0.25
     Sabb
    0.24
     dred
    0.24
    ifacts
    0.23
    æĺŁçº§éħĴåºĹ
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.