© 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. 129865
    Prev
    Next
    INDEX
    Explanations

    Aneurysm

    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
    (vol
    -0.26
    ÑĢеб
    -0.26
    uling
    -0.25
    pler
    -0.24
    ilio
    -0.24
    UPLE
    -0.24
    个交æĺĵ
    -0.24
    æ¯Ľ
    -0.23
     arrived
    -0.23
    allery
    -0.23
    POSITIVE LOGITS
    eur
    0.28
    å¾¼
    0.27
    æĥ¨
    0.25
    urban
    0.25
    [](
    0.24
    æĺ¾çĦ¶
    0.23
    æĺ¾çĦ¶æĺ¯
    0.23
     bü
    0.23
    çľĭä¸Ģçľĭ
    0.23
     öz
    0.23
    Activations Density 3.502%

    No Known Activations