© 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. 130494
    Prev
    Next
    INDEX
    Explanations

    Actions being performed or changed

    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
    æĬĽ
    -0.26
    丢
    -0.26
    éĩįä¸Ńä¹ĭéĩį
    -0.26
    irl
    -0.25
     tung
    -0.25
    æīĶ
    -0.25
    LOSE
    -0.25
    ä¾Ŀæ³ķ
    -0.24
     smugg
    -0.24
    edBy
    -0.24
    POSITIVE LOGITS
    udes
    0.32
    lite
    0.31
    ngr
    0.26
     Ravens
    0.24
    aru
    0.24
    æīįè¡Į
    0.24
    éĥ½æľīèĩªå·±
    0.24
    UGIN
    0.24
    aya
    0.23
    uvian
    0.23
    Activations Density 50.531%

    No Known Activations