© 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. 23-TRANSCODER-HP
    7. 25325
    Prev
    Next
    INDEX
    Explanations

    commonality, shared elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    READY
    -0.27
    oriously
    -0.26
    shots
    -0.24
     Sweep
    -0.24
    ä¸įåłª
    -0.24
    å¾Ī满æĦı
    -0.24
    orious
    -0.23
    еÑĩа
    -0.23
    GetCurrent
    -0.23
     dela
    -0.23
    POSITIVE LOGITS
     shared
    0.78
    åħ±åIJĮ
    0.77
     Shared
    0.70
    shared
    0.67
    Shared
    0.66
    åħ±äº«
    0.57
    -shared
    0.56
     common
    0.56
    _shared
    0.55
     gemeins
    0.54
    Activations Density 0.010%

    No Known Activations