© 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. 88887
    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
    nar
    -0.25
    å±ĢéĿ¢
    -0.25
    .Extension
    -0.24
    è¿ľæĸ¹
    -0.24
    çĻ¾å¹´
    -0.24
    egral
    -0.24
    ,System
    -0.24
    å®ĮäºĨ
    -0.23
    èij©
    -0.23
    æļ§æĺ§
    -0.23
    POSITIVE LOGITS
    affer
    0.32
    ocks
    0.25
    åĪĿä¸ī
    0.23
    LinkId
    0.23
    basket
    0.23
    utterstock
    0.23
    OwnerId
    0.23
    ensex
    0.23
    iers
    0.23
     owners
    0.23
    Activations Density 2.443%

    No Known Activations

    This feature has no known activations.