© 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. 245
    Prev
    Next
    INDEX
    Explanations

    Keith

    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
     deferred
    -0.26
    Void
    -0.26
    /man
    -0.25
    arcer
    -0.24
     poles
    -0.24
    nets
    -0.24
    .Surface
    -0.23
    _Vector
    -0.23
    æĢĤ
    -0.23
    èĤ¡æľ¬
    -0.23
    POSITIVE LOGITS
     Ir
    0.29
    ç»IJ
    0.28
    åĽĽæĸ¹
    0.27
    ä¸įå®ļ
    0.25
    peer
    0.25
     sweets
    0.24
     rend
    0.24
    otte
    0.24
    iek
    0.23
    åĬ¬
    0.23
    Activations Density 0.009%

    No Known Activations