© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 236
    Prev
    Next
    INDEX
    Explanations

    bone and variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .combine
    -0.27
    ãģ¾ãģĽ
    -0.25
     Buen
    -0.25
    çī§
    -0.25
    ãĢħ
    -0.24
    idor
    -0.24
    èģĮä¸ļ
    -0.24
    xis
    -0.24
    imit
    -0.24
    åĸĦ
    -0.23
    POSITIVE LOGITS
    trys
    0.31
    shore
    0.25
    åĴĮæľįåĬ¡
    0.25
     planet
    0.25
     fellowship
    0.25
    _ssh
    0.25
    serter
    0.24
     TempData
    0.24
    <br
    0.24
     credential
    0.23
    Activations Density 0.026%

    No Known Activations