© 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. 41233
    Prev
    Next
    INDEX
    Explanations

    measurement, rates, physical properties

    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
    ç²Ĺç³Ļ
    -0.31
    yme
    -0.31
     densities
    -0.30
    aver
    -0.28
    çİĩè¾¾
    -0.27
     averages
    -0.27
     tastes
    -0.26
    åıijçĹħçİĩ
    -0.26
     Everywhere
    -0.26
    ç¨İçİĩ
    -0.25
    POSITIVE LOGITS
    大å°ı
    0.40
     size
    0.35
    [size
    0.34
    _Size
    0.34
    .size
    0.31
    GetSize
    0.31
     getSize
    0.31
    _size
    0.30
     Size
    0.30
    size
    0.29
    Activations Density 2.869%

    No Known Activations