© 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. 88561
    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
     unwrap
    -0.26
    .','
    -0.24
    æī¹
    -0.24
    iola
    -0.24
    /rand
    -0.24
    ');č↵č↵
    -0.23
     plot
    -0.23
     mis
    -0.23
    ipsis
    -0.23
    .',č↵
    -0.23
    POSITIVE LOGITS
    æIJº
    0.28
    _visitor
    0.26
    oppers
    0.26
    ltre
    0.25
    å°±è¿ŀ
    0.24
     relational
    0.24
    ony
    0.24
    æĿİåħĪçĶŁ
    0.24
    ltr
    0.24
    -primary
    0.24
    Activations Density 41.183%

    No Known Activations

    This feature has no known activations.