© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    à¹Ģà¸Ńà¸ģ
    -0.28
    .ur
    -0.25
    éĽ
    -0.25
    spinner
    -0.24
    arty
    -0.24
    æIJĶ
    -0.24
    çĪ±äºº
    -0.24
    rupt
    -0.24
    马åħĭæĢĿ
    -0.24
    insky
    -0.23
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.27
    件
    0.27
    ebb
    0.27
    éĩį建
    0.26
    æīįèĥ½
    0.25
    åį³ä½¿
    0.25
     fled
    0.24
    åºĶä»ĺ
    0.24
    lings
    0.24
    glas
    0.24
    Activations Density 0.353%

    No Known Activations