© 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. 89076
    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
    uras
    -0.29
    metis
    -0.27
    ialog
    -0.27
    ckt
    -0.27
    asher
    -0.26
    æĪIJé¾Ļ
    -0.25
    imately
    -0.24
    inus
    -0.24
    SUP
    -0.23
    stakes
    -0.23
    POSITIVE LOGITS
    iting
    0.26
    ä¸Ģ个æĸ°çļĦ
    0.25
     subscribing
    0.25
    æĪijè®°å¾Ĺ
    0.25
    å°ı康
    0.25
    æĸ°ä¸ī
    0.24
    åĪ°æľŁ
    0.24
    è´
    0.24
    åħīçħ§
    0.24
    éĻ¤éĿŀ
    0.24
    Activations Density 1.008%

    No Known Activations

    This feature has no known activations.