© 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. 12-TRANSCODER-HP
    7. 23024
    Prev
    Next
    INDEX
    Explanations

    Email headers and foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩºçİ°
    -0.27
    erer
    -0.26
    eger
    -0.26
     appearing
    -0.25
     Appe
    -0.25
    |[
    -0.25
    ToF
    -0.24
    igli
    -0.24
    大çģ«
    -0.24
    _far
    -0.23
    POSITIVE LOGITS
    resh
    0.29
    åİĭåĬĽ
    0.27
    å£ĵåĬĽ
    0.24
     Encyclopedia
    0.24
    rides
    0.24
    æĶ¹è£ħ
    0.24
    amps
    0.24
    -General
    0.23
    opher
    0.23
     Translation
    0.23
    Activations Density 0.001%

    No Known Activations