© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24003
    Prev
    Next
    INDEX
    Explanations

    follow

    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
    Negative Logits
    INARY
    -0.28
    蹶
    -0.26
    éĨº
    -0.26
    æĻ¾
    -0.25
    atories
    -0.24
    æ¼Ĥæµģ
    -0.24
    踬
    -0.24
    åŁº
    -0.24
    EXTERNAL
    -0.24
     GIR
    -0.24
    POSITIVE LOGITS
    ago
    0.28
    cycle
    0.27
    æŶæķĪ
    0.26
    AGO
    0.26
     ago
    0.26
     Plan
    0.25
    éĩijèī²
    0.25
     зад
    0.24
    let
    0.24
     individually
    0.24
    Activations Density 0.005%

    No Known Activations