© 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. 90336
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    opic
    -0.29
    OID
    -0.28
    åĪļéľĢ
    -0.25
    Dire
    -0.24
     organised
    -0.24
     scares
    -0.24
    hta
    -0.24
    IBM
    -0.23
     irritated
    -0.23
     Mick
    -0.23
    POSITIVE LOGITS
    novation
    0.28
    ylim
    0.28
    çĦ¶åIJİåĨį
    0.27
    å®ĥåı¯ä»¥
    0.27
    å¼¹
    0.26
    reme
    0.25
    yper
    0.25
    amat
    0.25
    atern
    0.25
     correction
    0.25
    Activations Density 4.433%

    No Known Activations