© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90045
    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
    amiliar
    -0.28
     roller
    -0.26
    rox
    -0.26
    侥幸
    -0.25
     libertine
    -0.24
    masked
    -0.24
    errorCode
    -0.24
    åľ°
    -0.24
    rego
    -0.23
    èĭ
    -0.23
    POSITIVE LOGITS
    ç«łç¨ĭ
    0.26
     Se
    0.25
    åħĪ导
    0.25
    æĭīçĿĢ
    0.25
     главное
    0.25
    æľºèĥ½
    0.24
     behind
    0.24
    Handles
    0.24
    缦
    0.24
    åºĶ该å¦Ĥä½ķ
    0.24
    Activations Density 9.507%

    No Known Activations

    This feature has no known activations.