© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40541
    Prev
    Next
    INDEX
    Explanations

    Discrimination and prejudice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıł
    -0.27
    haar
    -0.25
    åı³
    -0.24
    ä»įæľª
    -0.24
     heavier
    -0.24
    aryl
    -0.24
     hat
    -0.24
    ++.
    -0.24
     Hampton
    -0.23
    è¾ī
    -0.23
    POSITIVE LOGITS
    acles
    0.29
    .Dot
    0.27
    ä¸ªé¡¹çĽ®
    0.26
    ancial
    0.25
    crypt
    0.24
    contre
    0.24
    VERT
    0.23
    åĶij
    0.23
     запиÑģи
    0.23
    .ua
    0.23
    Activations Density 0.914%

    No Known Activations