© 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. 64311
    Prev
    Next
    INDEX
    Explanations

    reverse

    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
    elon
    -0.27
    åľª
    -0.26
     Heard
    -0.26
    تÙĪر
    -0.25
    Ion
    -0.25
     Irr
    -0.25
    åı¦ä¸Ģä½į
    -0.25
    .DisplayName
    -0.25
    gings
    -0.24
    }}],↵
    -0.24
    POSITIVE LOGITS
    abal
    0.29
     previous
    0.28
    prev
    0.27
     prev
    0.27
    able
    0.27
     terms
    0.26
    åIJİçļĦ
    0.26
    ä¸ĬæĿ¥
    0.25
    ä¹ĭåīįçļĦ
    0.25
    -ac
    0.25
    Activations Density 11.123%

    No Known Activations