© 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. 107045
    Prev
    Next
    INDEX
    Explanations

    proving

    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
    éģį
    -0.24
    gam
    -0.24
    оÑī
    -0.23
    åħ¥åĽŃ
    -0.23
    代åĬŀ
    -0.23
     Apostle
    -0.23
    alist
    -0.23
     lá
    -0.23
    gest
    -0.23
    åľ¨è¿ĩæ¸¡æľŁ
    -0.23
    POSITIVE LOGITS
     synchronous
    0.27
    æľī幸
    0.27
     snug
    0.27
     societies
    0.26
    SION
    0.26
    -zone
    0.25
    onium
    0.25
    íļį
    0.24
     ExecutionContext
    0.23
    æĥŁ
    0.23
    Activations Density 12.350%

    No Known Activations