© 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. 88584
    Prev
    Next
    INDEX
    Explanations

    time

    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
    -than
    -0.28
    ipients
    -0.25
    pite
    -0.24
    imit
    -0.23
    ç¥Ń
    -0.23
    æľªæĿ¥çļĦ
    -0.23
    isp
    -0.23
     future
    -0.23
    outine
    -0.23
    fen
    -0.23
    POSITIVE LOGITS
    --[
    0.28
    åĨĮ
    0.25
    å°±æĥ³
    0.25
    两åı¥
    0.24
     supposedly
    0.24
    john
    0.24
    åĿŀ
    0.24
     supposed
    0.24
    æµij身
    0.24
    åıijå±ķåīįæĻ¯
    0.24
    Activations Density 10.411%

    No Known Activations