© 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. 33-TRANSCODER-HP
    7. 54306
    Prev
    Next
    INDEX
    Explanations

    biographies and news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ele
    -0.28
    FFF
    -0.27
    _accept
    -0.27
    utral
    -0.25
    aff
    -0.25
    èĽĭ
    -0.25
    /git
    -0.25
    arg
    -0.24
    ilty
    -0.24
    .hxx
    -0.24
    POSITIVE LOGITS
    alom
    0.27
    åѦ
    0.24
    icc
    0.24
    ä¼ī
    0.24
    alem
    0.24
    libs
    0.24
    ped
    0.23
    ä¸į让
    0.23
    æľīä¸Ģç§į
    0.23
    æĻŁ
    0.23
    Activations Density 0.035%

    No Known Activations