© 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. 141912
    Prev
    Next
    INDEX
    Explanations

    informal 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
    é¦IJ
    -0.27
    -aff
    -0.27
    訪
    -0.26
     views
    -0.25
    nez
    -0.25
     каÑĤегоÑĢии
    -0.25
    kB
    -0.24
    ä»ĺ
    -0.24
    ();)
    -0.24
    访
    -0.24
    POSITIVE LOGITS
    hardt
    0.26
    ystone
    0.26
    çļĦä¼ĺåĬ¿
    0.25
     IQueryable
    0.25
     Effect
    0.24
     Iterable
    0.24
    pile
    0.23
    rut
    0.23
    eli
    0.23
    subtype
    0.23
    Activations Density 6.781%

    No Known Activations