© 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. 33-TRANSCODER-HP
    7. 53220
    Prev
    Next
    INDEX
    Explanations

    say "ar" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pt
    -0.28
    lean
    -0.28
     pd
    -0.27
    ptive
    -0.26
     es
    -0.26
     tower
    -0.26
     PD
    -0.25
    ant
    -0.25
     em
    -0.25
     Democratic
    -0.25
    POSITIVE LOGITS
    äºĭå®ŀ
    0.33
    红楼
    0.29
     fact
    0.29
     ÑĦакÑĤ
    0.29
    fact
    0.28
    aar
    0.27
    RAR
    0.27
     Fact
    0.27
    VISION
    0.27
    manual
    0.26
    Activations Density 0.011%

    No Known Activations