© 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. 89946
    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
     influencers
    -0.29
    appe
    -0.27
    èĸ¤
    -0.27
    -corner
    -0.26
     durable
    -0.26
    atics
    -0.26
     believing
    -0.26
     Permanent
    -0.25
     permanent
    -0.25
    isters
    -0.24
    POSITIVE LOGITS
    èѦ
    0.29
    æĪĸå¤ļ
    0.28
    转
    0.27
     concession
    0.26
    èĻļ
    0.26
    utenberg
    0.25
    éĴ¦
    0.25
    æĬµ
    0.25
    Nat
    0.24
     Deprecated
    0.24
    Activations Density 34.590%

    No Known Activations

    This feature has no known activations.