© 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. 88340
    Prev
    Next
    INDEX
    Explanations

    Rewards

    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
    wise
    -0.26
     collapsed
    -0.26
    æķĪ
    -0.26
    porate
    -0.25
    ctions
    -0.25
    jab
    -0.24
    ouse
    -0.24
    pisa
    -0.24
    ç®ĹäºĨ
    -0.24
    åįķçĭ¬
    -0.24
    POSITIVE LOGITS
     mel
    0.28
    banks
    0.26
    (resultado
    0.26
    éŨ
    0.25
    uy
    0.25
    缣
    0.24
     banks
    0.24
    dj
    0.24
    æĥ³åĥı
    0.24
    çļĦ身份
    0.23
    Activations Density 4.922%

    No Known Activations