© 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. 18-TRANSCODER-HP
    7. 89031
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    积åĪĨ
    -0.28
    ene
    -0.27
    ãĤ³ãĥ³ãĥĨãĥ³ãĥĦ
    -0.26
    贪婪
    -0.25
    uelle
    -0.25
    æľ
    -0.24
    liced
    -0.24
    åĿĩåĮĢ
    -0.24
    ueue
    -0.24
    ìĽ¨
    -0.24
    POSITIVE LOGITS
    leaning
    0.26
    åĢ¾æĸľ
    0.25
    dden
    0.25
     Dun
    0.25
    ä¸īæĸ¹
    0.25
    iki
    0.24
    FORMAT
    0.24
    é«¡
    0.24
     triple
    0.24
    _different
    0.24
    Activations Density 4.129%

    No Known Activations