© 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. 22605
    Prev
    Next
    INDEX
    Explanations

    first of its kind

    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
    å¾ĢåIJİ
    -0.33
    æľīæķĪæĢ§
    -0.27
    VertexArray
    -0.26
    åĶ³
    -0.26
    idot
    -0.26
    åħĪæĬĬ
    -0.25
    iente
    -0.25
     scramble
    -0.24
    æĮĤ
    -0.24
    è°ĥåĬ¨
    -0.24
    POSITIVE LOGITS
    çµ®
    0.28
     Intelli
    0.27
    puter
    0.26
    POWER
    0.25
    kol
    0.25
    Åı
    0.24
    åĬ¿
    0.24
    itage
    0.24
    ghan
    0.24
    LING
    0.24
    Activations Density 0.001%

    No Known Activations