© 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. 141406
    Prev
    Next
    INDEX
    Explanations

    -ing

    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
     deeply
    -0.26
    年第
    -0.26
     already
    -0.25
    'util
    -0.25
    ä¾ĽåĽ¾
    -0.24
     originally
    -0.24
    ArrayType
    -0.24
     Infect
    -0.24
     frequently
    -0.23
    "People
    -0.23
    POSITIVE LOGITS
    åģ·
    0.29
    abilia
    0.27
    aire
    0.26
    atts
    0.25
    att
    0.25
    ä»Ķ
    0.25
    rompt
    0.24
    åĵģä½į
    0.24
    æĮij
    0.24
    NEL
    0.24
    Activations Density 17.056%

    No Known Activations