© 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. 141746
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ouples
    -0.26
    æŀľ
    -0.26
    .generated
    -0.25
     Mak
    -0.25
     Schwe
    -0.24
    å¼ĤæĢ§
    -0.24
    豫
    -0.24
    lesia
    -0.24
     Better
    -0.24
    creen
    -0.24
    POSITIVE LOGITS
    å±ĭéĩĮ
    0.27
    metry
    0.25
    ilda
    0.25
    为æ°ij
    0.25
    ique
    0.24
    mlin
    0.24
    å¸Ŀ
    0.24
     set
    0.24
     party
    0.23
    avar
    0.23
    Activations Density 90.295%

    No Known Activations