© 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. 20-TRANSCODER-HP
    7. 64252
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłå½¢
    -0.27
     regress
    -0.26
    æĹ¶æľŁçļĦ
    -0.25
     r
    -0.25
    管çIJĨå±Ĥ
    -0.25
    맥
    -0.24
    hel
    -0.24
    fy
    -0.24
    å½¢æĪIJäºĨ
    -0.24
    没ä»Ģä¹Ī
    -0.24
    POSITIVE LOGITS
    entine
    0.28
     Winn
    0.27
     Hague
    0.26
    è¹²
    0.26
    _delivery
    0.26
    attachments
    0.26
    å¸Ń
    0.26
    nowrap
    0.25
    gue
    0.25
     minced
    0.25
    Activations Density 5.870%

    No Known Activations