© 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. 22-TRANSCODER-HP
    7. 112285
    Prev
    Next
    INDEX
    Explanations

    code keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edList
    -0.31
    edException
    -0.30
    ayout
    -0.28
     Cole
    -0.27
    ElementsByTagName
    -0.26
    edo
    -0.26
     capital
    -0.26
    hang
    -0.25
    æѤæĻĤ
    -0.25
     til
    -0.25
    POSITIVE LOGITS
    å¾Īå°ı
    0.28
    å¾Īéķ¿
    0.27
    å¾Īéĩįè¦ģ
    0.27
    å¾Īé«ĺ
    0.27
    å¾Īä½İ
    0.25
    rib
    0.25
    éĿŀ常éĩįè¦ģ
    0.24
    supports
    0.24
     nuestros
    0.24
     Tus
    0.24
    Activations Density 0.001%

    No Known Activations