© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62846
    Prev
    Next
    INDEX
    Explanations

    variety of articles

    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
    dra
    -0.28
    æ²¥
    -0.27
    å§ĭ
    -0.26
    Ļ¶
    -0.26
     Sims
    -0.26
    å¹³æ°ij
    -0.25
    ords
    -0.24
    aur
    -0.24
    DI
    -0.24
    æĸ¹å¼ı
    -0.24
    POSITIVE LOGITS
    rame
    0.25
    rox
    0.25
    ainen
    0.24
     Features
    0.24
    èŀºæĹĭ
    0.23
    è±
    0.23
    ä¼ĺè´¨
    0.23
    ä¸įèī¯ä¿¡æģ¯
    0.23
    redux
    0.22
    iance
    0.22
    Activations Density 16.352%

    No Known Activations