© 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. 130251
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
    ä¿Ŀ
    -0.28
    弥补
    -0.27
    ido
    -0.27
     Miss
    -0.26
    å±ĭ
    -0.25
     missed
    -0.25
     Kunden
    -0.25
     Sense
    -0.24
    nish
    -0.24
    æľªèĥ½
    -0.23
    POSITIVE LOGITS
    aec
    0.28
    æĴķ
    0.28
    .tk
    0.27
    BufferData
    0.25
    ·»
    0.25
    onder
    0.24
    åŃĵ
    0.24
    usra
    0.24
     currentDate
    0.24
    ieu
    0.23
    Activations Density 38.144%

    No Known Activations