© 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. 141179
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    rement
    -0.28
    ÅŁtur
    -0.27
    (auto
    -0.27
    actice
    -0.26
    adies
    -0.26
    海绵
    -0.24
     amnesty
    -0.24
    å¥ļ
    -0.24
    åı¸æ³ķ
    -0.24
    ä¸įçĦ¶
    -0.24
    POSITIVE LOGITS
    stakes
    0.28
    scope
    0.27
    ä¸Ģ页
    0.26
    akis
    0.25
     Input
    0.24
     Rita
    0.24
    Input
    0.24
    ITS
    0.24
    GED
    0.23
    椽
    0.23
    Activations Density 6.993%

    No Known Activations