© 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. 88995
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    æĩ·
    -0.29
    sure
    -0.29
    æĢĢ
    -0.28
    berry
    -0.28
    ALAR
    -0.26
    grass
    -0.25
    èĦijæµ·ä¸Ń
    -0.25
    èĥŃ
    -0.25
     Paran
    -0.25
    sz
    -0.24
    POSITIVE LOGITS
    è¨Ģ
    0.31
    å¾Ģ
    0.31
    (formatter
    0.26
    æĸĩåĮĸçļĦ
    0.26
     resil
    0.25
    apse
    0.25
     dipl
    0.25
     --
    0.24
    ç»Ī
    0.24
    æ¿¡
    0.24
    Activations Density 17.549%

    No Known Activations