© 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. 88487
    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
    _lc
    -0.26
    primitive
    -0.25
    odesk
    -0.25
    vented
    -0.24
    resher
    -0.24
    ÑĢеб
    -0.23
    å¦Ĵ
    -0.23
    oproject
    -0.23
     Lair
    -0.23
    vertise
    -0.23
    POSITIVE LOGITS
    询éĹ®
    0.32
    åIJ¬
    0.32
    Asked
    0.30
    æĹłäººæľº
    0.28
    oney
    0.28
     thu
    0.27
    bin
    0.26
    è§Ĩè§ī
    0.26
    è§ĨåIJ¬
    0.25
    éĹ®
    0.25
    Activations Density 1.151%

    No Known Activations

    This feature has no known activations.