© 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. 90320
    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
    Negative Logits
    ronym
    -0.30
    åįľ
    -0.26
    ÑĤин
    -0.25
     Lawn
    -0.25
    èĢĮåĩº
    -0.25
    FFF
    -0.25
    æľĪ以æĿ¥
    -0.25
    åĮ¿
    -0.24
    juan
    -0.24
    estring
    -0.24
    POSITIVE LOGITS
    å·¾
    0.29
    irit
    0.26
    evity
    0.26
     intox
    0.26
     extracts
    0.25
     confisc
    0.25
     intoxic
    0.25
     decorative
    0.25
     defiance
    0.25
     coff
    0.24
    Activations Density 0.151%

    No Known Activations

    This feature has no known activations.