© 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. 151416
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    ngo
    -0.25
    GES
    -0.24
    bcd
    -0.24
    worth
    -0.24
    IAN
    -0.24
    zier
    -0.23
    dcc
    -0.23
    /tcp
    -0.23
     pian
    -0.23
    åħ³èģĶ交æĺĵ
    -0.23
    POSITIVE LOGITS
     intr
    0.28
    åľ¨åIJĮä¸Ģ
    0.27
     masked
    0.25
     extr
    0.25
    å®
    0.24
    ç¼°
    0.24
    _intr
    0.24
    纺
    0.23
    };↵
    0.23
    intr
    0.23
    Activations Density 0.593%

    No Known Activations