© 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. 64320
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    pedia
    -0.30
    åį¿
    -0.26
    aidu
    -0.25
    æĺ¯ä»¥
    -0.25
     Tome
    -0.24
    è¿ĩæĿ¥
    -0.24
    å°±éľĢè¦ģ
    -0.24
     ASA
    -0.24
    ãĤ·ãĥ¼
    -0.23
    heiten
    -0.23
    POSITIVE LOGITS
    çĸ£
    0.32
    isel
    0.28
     placeholder
    0.26
    LastError
    0.26
     fatt
    0.25
     pall
    0.25
    asser
    0.25
    jal
    0.25
    æĬ±
    0.25
     flawed
    0.24
    Activations Density 4.589%

    No Known Activations