© 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. 0
    Prev
    Next
    INDEX
    Explanations

    age

    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
    èĩ»
    -0.29
    ÑĤик
    -0.26
    uff
    -0.26
     discontin
    -0.26
     high
    -0.26
    ields
    -0.26
    util
    -0.25
    Å°
    -0.25
    etics
    -0.25
     Citation
    -0.25
    POSITIVE LOGITS
    shed
    0.27
    -out
    0.24
    samp
    0.24
     unsuccessfully
    0.24
    snow
    0.24
    needle
    0.23
    hall
    0.23
    ">%
    0.23
    å¹´ç»Ī
    0.23
    央
    0.22
    Activations Density 0.029%

    No Known Activations