© 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. 14-TRANSCODER-HP
    7. 40790
    Prev
    Next
    INDEX
    Explanations

    York

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    preter
    -0.28
    fans
    -0.27
    æ¯Ķäºļ
    -0.26
    åĪ¶èį¯
    -0.26
    kos
    -0.25
    åģ¥åº·çļĦ
    -0.24
    çĽ¾
    -0.24
    slack
    -0.23
    StreamReader
    -0.23
     tape
    -0.23
    POSITIVE LOGITS
    âĹĦ
    0.29
    ENA
    0.28
     sát
    0.27
    eguard
    0.26
    ân
    0.25
    æĽ´éĩįè¦ģçļĦ
    0.25
    çīµå¼ķ
    0.25
    á»Ķ
    0.24
    èį·èĬ±
    0.24
    ena
    0.24
    Activations Density 0.269%

    No Known Activations