© 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. 19-TRANSCODER-HP
    7. 7665
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨå¸ĥåľ¨
    -0.26
    yro
    -0.26
    éĩijèŀįåį±æľº
    -0.26
    .tk
    -0.26
     Madden
    -0.25
    è¡®
    -0.24
    growth
    -0.24
    æľĢå¿«
    -0.24
    ConfigurationException
    -0.24
    mandatory
    -0.24
    POSITIVE LOGITS
     particular
    0.29
    ems
    0.29
    é¼İ
    0.28
    详解
    0.27
    emat
    0.27
    çī¹å®ļ
    0.27
     definit
    0.26
    าà¸Ļ
    0.26
     specific
    0.26
    ât
    0.26
    Activations Density 0.031%

    No Known Activations