© 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. 18-TRANSCODER-HP
    7. 89853
    Prev
    Next
    INDEX
    Explanations

    Names and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĴĮ个人
    -0.29
     Fixture
    -0.29
    plaint
    -0.29
    fixture
    -0.28
    lessly
    -0.27
     fixture
    -0.25
    iless
    -0.25
    -bed
    -0.25
    åĬĽ
    -0.24
    aroo
    -0.24
    POSITIVE LOGITS
    çŁ¥éģĵäºĨ
    0.30
    åľ»
    0.28
    赶æĿ¥
    0.26
    稳å®ļçļĦ
    0.26
    æĸ°åĬł
    0.25
    ç´ł
    0.25
    ä¸īåĪĨ
    0.25
    赶åĪ°
    0.25
    ÏĬ
    0.24
    éĴĻ
    0.24
    Activations Density 4.891%

    No Known Activations