© 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. 111392
    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_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
     createAction
    -0.28
    æĶ¶æĶ¯
    -0.27
     IBOutlet
    -0.25
    createClass
    -0.24
    '),('
    -0.23
    usted
    -0.23
    uzu
    -0.23
    č↵	č↵
    -0.23
    []č↵
    -0.23
     pud
    -0.23
    POSITIVE LOGITS
    jaw
    0.26
    elter
    0.26
    åŁĭ
    0.26
    untlet
    0.24
    æģ¶æĦı
    0.24
    os
    0.24
    é¡į
    0.24
    ipers
    0.24
    urable
    0.23
    ä¸Ģæīĭ
    0.23
    Activations Density 0.100%

    No Known Activations