© 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. 24-TRANSCODER-HP
    7. 150863
    Prev
    Next
    INDEX
    Explanations

    programming/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edelta
    -0.26
    è¿ĺ好
    -0.26
    ilon
    -0.26
    trä
    -0.25
     Lage
    -0.24
     recurs
    -0.24
    ä»Ħ
    -0.24
    åħ³äºİæĪij们
    -0.23
     backstage
    -0.23
     HCI
    -0.23
    POSITIVE LOGITS
    osas
    0.29
    éĢĶ
    0.28
    é¢Ŀ
    0.28
    getReference
    0.27
    addir
    0.26
    æĮĩæĮ¥
    0.25
    reff
    0.25
    ãĥ¼ãĤº
    0.24
    éĻIJ
    0.24
    iller
    0.24
    Activations Density 0.031%

    No Known Activations