© 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. 18-TRANSCODER-HP
    7. 89521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以人为
    -0.28
     Laurel
    -0.28
    éģģ
    -0.27
    ÐłÐķ
    -0.27
    èĹģ
    -0.25
    æīĢ以说
    -0.25
    rie
    -0.25
     GOT
    -0.25
     Valent
    -0.24
    @author
    -0.24
    POSITIVE LOGITS
     inv
    0.27
    apur
    0.27
     sideways
    0.25
     em
    0.25
    ems
    0.25
    æĢµ
    0.25
    ilos
    0.25
     ZZ
    0.25
    å±ķ
    0.24
     fis
    0.24
    Activations Density 4.687%

    No Known Activations

    This feature has no known activations.