© 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. 88640
    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
    åľĪ
    -0.27
     pent
    -0.27
     Chrom
    -0.26
     fringe
    -0.26
    æıļ
    -0.25
    ìĹ´
    -0.25
    chrom
    -0.25
    èIJ¥åĪ©
    -0.25
    æī¬
    -0.25
     Rockefeller
    -0.25
    POSITIVE LOGITS
    çĪ±äºº
    0.31
     ÅŁ
    0.28
    ãĥĭãĤ¢
    0.27
    /mm
    0.26
    微信åı·
    0.25
    .pick
    0.25
    Upload
    0.24
    ANTA
    0.24
     Upload
    0.24
     savoir
    0.24
    Activations Density 48.451%

    No Known Activations

    This feature has no known activations.