© 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. 53676
    Prev
    Next
    INDEX
    Explanations

    geographical/administrative divisions

    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
     mon
    -0.32
    aticon
    -0.27
    éĴŁ
    -0.27
     disposing
    -0.27
    mon
    -0.26
    _plate
    -0.25
    Borders
    -0.25
    åĺ´è§Ĵ
    -0.25
     dips
    -0.25
     chart
    -0.25
    POSITIVE LOGITS
    æµĩ
    0.27
    orate
    0.26
    å¾Īå°ı
    0.26
    oe
    0.26
    èĢ¶
    0.24
    å±İ
    0.24
    institution
    0.24
    éĢļ车
    0.23
     Instit
    0.23
     institutional
    0.23
    Activations Density 0.013%

    No Known Activations