© 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. 88150
    Prev
    Next
    INDEX
    Explanations

    Books, guides, systems

    np_max-act · gemini-2.0-flash
    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
     scrim
    -0.28
    çļĦä¸ĢäºĽ
    -0.25
    åıijè§ī
    -0.25
    eea
    -0.25
     Term
    -0.24
    æĬ¬èµ·
    -0.24
    æĢ»åħ±
    -0.24
    ests
    -0.23
    oksen
    -0.23
    ergic
    -0.23
    POSITIVE LOGITS
    ition
    0.30
     Guinness
    0.27
    ius
    0.27
    æµĵ缩
    0.26
    cient
    0.26
    æ²»
    0.25
     consolidated
    0.25
    TED
    0.24
     separate
    0.24
    javax
    0.24
    Activations Density 6.463%

    No Known Activations