© 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. 108271
    Prev
    Next
    INDEX
    Explanations

    single digits

    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
    å¸
    -0.28
    éĿ¢åŃĶ
    -0.27
    heits
    -0.26
    illing
    -0.26
    essen
    -0.26
    pac
    -0.25
    bé
    -0.25
    avers
    -0.25
     sounding
    -0.25
    å¿Ĵ
    -0.25
    POSITIVE LOGITS
    åIJĦåİ¿
    0.31
    åIJĦåĮº
    0.29
    æıIJåĢ¡
    0.28
    odem
    0.27
    PLICATION
    0.26
    ados
    0.26
    аÑĢам
    0.25
    enez
    0.25
    æĮij
    0.25
    äºĨåIJ§
    0.25
    Activations Density 1.706%

    No Known Activations