© 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. 63053
    Prev
    Next
    INDEX
    Explanations

    Random snippets of text

    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
     nomination
    -0.27
     nominations
    -0.25
    parser
    -0.25
    eca
    -0.25
    ca
    -0.24
    cr
    -0.24
    Nom
    -0.23
    æĭ¿åĪ°äºĨ
    -0.23
    crate
    -0.23
    nom
    -0.23
    POSITIVE LOGITS
    ани
    0.28
    lij
    0.25
    æ¯ĶåĪ©
    0.25
    æ³Ĭ
    0.24
    æī¯
    0.24
     Humanity
    0.24
    åIJĮæ¯Ķ
    0.24
    è°¤
    0.24
     Territory
    0.23
    ItemImage
    0.23
    Activations Density 52.201%

    No Known Activations