© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41613
    Prev
    Next
    INDEX
    Explanations

    Religion and technical content

    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
    Negative Logits
    çĸĹ
    -0.29
    å±Ģ
    -0.28
    åĩ»
    -0.27
     Tele
    -0.27
    éļľç¢į
    -0.26
    (Py
    -0.25
    é¡
    -0.24
    Vk
    -0.24
    çĶ«
    -0.24
    éģ¥æݧ
    -0.24
    POSITIVE LOGITS
     Papers
    0.26
    andler
    0.25
    çĪĨåĩº
    0.24
    ä¸ĵåĮº
    0.24
     поÑģÑĤоÑı
    0.24
    esModule
    0.24
     Abed
    0.23
     papers
    0.23
     natur
    0.23
     configFile
    0.23
    Activations Density 1.077%

    No Known Activations