© 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. 107718
    Prev
    Next
    INDEX
    Explanations

    of

    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
    EAR
    -0.28
    astro
    -0.27
    å¸
    -0.25
     Cush
    -0.25
    zÄħ
    -0.25
    mpr
    -0.24
    Chief
    -0.24
    åĽ¿
    -0.24
     communic
    -0.24
    è¦ģåģļåĪ°
    -0.24
    POSITIVE LOGITS
    aff
    0.28
    åĨµ
    0.27
     anne
    0.26
    empre
    0.26
     aff
    0.26
    å½ķçĶ¨
    0.25
     affine
    0.25
     monthly
    0.24
     tales
    0.24
    è¿Ļä¹Ī说
    0.24
    Activations Density 0.241%

    No Known Activations