© 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. 53045
    Prev
    Next
    INDEX
    Explanations

    legal and business contexts

    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
    é¦Ĩ
    -0.27
    owi
    -0.26
     esl
    -0.25
    onus
    -0.24
    -map
    -0.24
    roke
    -0.23
    oss
    -0.23
    лон
    -0.23
    à¥į
    -0.23
    omore
    -0.23
    POSITIVE LOGITS
    TRANSFER
    0.28
    é»ij
    0.27
    pragma
    0.27
    ie
    0.27
    toolbox
    0.26
    顽
    0.26
    /year
    0.26
    inema
    0.25
    é¦ĭ
    0.25
    urd
    0.25
    Activations Density 0.011%

    No Known Activations