© 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. 377
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    çķĻ
    -0.29
    elif
    -0.27
    OfWork
    -0.26
    èĥľåĪ©
    -0.26
    亦
    -0.25
    achu
    -0.25
    esimal
    -0.25
    gium
    -0.25
     Either
    -0.25
    midd
    -0.25
    POSITIVE LOGITS
     dearly
    0.27
     stance
    0.26
    举æĬ¥
    0.26
    [src
    0.26
    oders
    0.26
    責
    0.25
    iali
    0.25
    èĤ¡æĮĩ
    0.25
    éĶµ
    0.24
    éĿĽ
    0.24
    Activations Density 0.060%

    No Known Activations