© 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. 24-TRANSCODER-HP
    7. 149143
    Prev
    Next
    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     LayoutInflater
    -0.28
     tabIndex
    -0.26
    idelberg
    -0.25
    ertas
    -0.25
    ByKey
    -0.24
    ertools
    -0.24
     fallback
    -0.24
     @[
    -0.24
    Fallback
    -0.24
    毡
    -0.23
    POSITIVE LOGITS
    www
    0.44
     www
    0.37
    èį£
    0.31
    sets
    0.28
    ose
    0.28
    鹿
    0.27
    设
    0.27
    íĺ¸
    0.27
    max
    0.26
    æī¶
    0.26
    Activations Density 0.252%

    No Known Activations