© 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. 40577
    Prev
    Next
    INDEX
    Explanations

    Scientific paper abstracts

    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
     fixtures
    -0.29
    иÑı
    -0.29
     Kut
    -0.27
    azz
    -0.27
    kin
    -0.27
    din
    -0.27
    ohen
    -0.25
    åIJijå¤ĸ
    -0.25
     sooner
    -0.25
    .asm
    -0.25
    POSITIVE LOGITS
    (AT
    0.29
    /wiki
    0.27
    ATOM
    0.26
    宵
    0.25
    -last
    0.25
    breadcrumb
    0.25
    yü
    0.25
     Fav
    0.25
     wg
    0.24
     mbox
    0.24
    Activations Density 0.047%

    No Known Activations