© 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. 142297
    Prev
    Next
    INDEX
    Explanations

    Formal text beginnings

    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
    ramework
    -0.28
    acin
    -0.24
    aint
    -0.24
    ewhere
    -0.24
     Cata
    -0.23
    å²Ľ
    -0.23
    ç¬ij
    -0.23
    lio
    -0.23
    intelligence
    -0.23
     responseType
    -0.23
    POSITIVE LOGITS
    åĮĻ
    0.28
    æݨåĩº
    0.27
    çĶµè§£
    0.26
    æ¿®
    0.25
    uele
    0.25
    æĥij
    0.24
    æĮģç»Ń
    0.24
     infusion
    0.24
    cut
    0.24
     overall
    0.24
    Activations Density 5.699%

    No Known Activations