© 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. 90085
    Prev
    Next
    INDEX
    Explanations

    Responsibility and representation

    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
    umps
    -0.25
    ://'
    -0.25
     Ñģамо
    -0.24
    acker
    -0.24
    ä¼łéĢģ
    -0.24
    kj
    -0.23
    åIJĪ
    -0.23
    ty
    -0.23
    åĭĺ
    -0.23
    ìłĪ
    -0.23
    POSITIVE LOGITS
    æľĢéļ¾
    0.28
    è¿Ļåĩł
    0.27
    ellas
    0.26
    isbn
    0.25
    ctic
    0.25
     Zug
    0.24
    encias
    0.24
    etten
    0.24
    ientes
    0.24
    å¾®
    0.24
    Activations Density 12.768%

    No Known Activations