© 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. 88565
    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
    eking
    -0.29
    utation
    -0.26
    æĪIJçĨŁ
    -0.25
    ailability
    -0.25
    efore
    -0.24
    InlineData
    -0.23
    樣
    -0.23
    aul
    -0.23
     translate
    -0.23
    preced
    -0.23
    POSITIVE LOGITS
     Dia
    0.27
    åħµ
    0.26
     wonders
    0.26
    议论
    0.26
     "!
    0.26
    ä¹ĭåĨħ
    0.25
    ãģijãģ¦
    0.23
     converse
    0.23
    è®®
    0.23
    çļĦ話
    0.23
    Activations Density 3.727%

    No Known Activations

    This feature has no known activations.