© 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. 89462
    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
    jos
    -0.30
    .compareTo
    -0.26
     proportion
    -0.26
    ä¸ĩä½Ļ
    -0.24
     composition
    -0.24
    -wrap
    -0.24
    sembled
    -0.23
    vox
    -0.23
    Pros
    -0.23
    ochond
    -0.23
    POSITIVE LOGITS
    .ce
    0.25
    èĦĪ
    0.24
    oins
    0.24
     unins
    0.24
    instein
    0.24
     Mirage
    0.23
     clit
    0.23
    adh
    0.23
    ournals
    0.23
    æ°ĸ
    0.23
    Activations Density 4.109%

    No Known Activations

    This feature has no known activations.