© 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. 88909
    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
    stands
    -0.26
    çĸij
    -0.26
    olars
    -0.26
    uled
    -0.25
    趣
    -0.25
    åĪºæ¿Ģ
    -0.25
    ç¾İ好çĶŁæ´»
    -0.24
    ?-
    -0.24
     focusing
    -0.24
    xiety
    -0.24
    POSITIVE LOGITS
    ertext
    0.29
     Chapters
    0.25
    ead
    0.25
    onium
    0.25
     Nimbus
    0.24
    è¿ĺæĺ¯è¦ģ
    0.24
    odon
    0.24
     Ðķго
    0.23
    _KHR
    0.23
    baru
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.