© 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
    2. Qwen3-4B
    3. 12-TRANSCODER-HP
    4. 23439
    Prev
    Next
    INDEX
    Explanations

    Anthrop

    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
     rem
    -0.33
    åĩĨç¡®æĢ§
    -0.30
     princip
    -0.28
    åħ¸åŀĭ
    -0.27
    accur
    -0.27
    edith
    -0.27
    edic
    -0.27
     inf
    -0.27
    adb
    -0.26
     listing
    -0.26
    POSITIVE LOGITS
    nels
    0.27
    æłª
    0.27
     tapped
    0.25
     ensued
    0.25
    æĭįåįĸ
    0.25
    计
    0.25
    ä¸ĢåĪĨ
    0.24
     createStore
    0.24
    Prov
    0.24
     Auction
    0.24
    Activations Density 0.003%

    No Known Activations