© 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. 88257
    Prev
    Next
    INDEX
    Explanations

    technical document snippets

    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
    .observe
    -0.27
    ieved
    -0.26
    /respond
    -0.26
    arring
    -0.26
    çªģåĽ´
    -0.25
    +(\
    -0.25
    èĩªæŁ¥
    -0.25
    èµĤ
    -0.25
    ç¯Ļ
    -0.25
    éĢģåĩº
    -0.25
    POSITIVE LOGITS
    onnement
    0.28
    suffix
    0.27
     preference
    0.25
    åIJİæİĴ
    0.25
     лиÑĨа
    0.25
    structural
    0.24
    ports
    0.24
    ái
    0.24
    nv
    0.24
    hib
    0.24
    Activations Density 7.893%

    No Known Activations