© 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. 89637
    Prev
    Next
    INDEX
    Explanations

    is/be

    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
    对æĪij们
    -0.32
    æĢĢ
    -0.31
    åħ·ä½ĵæĥħåĨµ
    -0.28
    说çļĦæĺ¯
    -0.27
    æĩ·
    -0.25
    åŁºæľ¬æĥħåĨµ
    -0.25
    ór
    -0.24
    Composition
    -0.24
     especÃŃf
    -0.24
    rary
    -0.24
    POSITIVE LOGITS
    稼
    0.29
     focus
    0.28
    åİ¥
    0.28
    erval
    0.26
    vinc
    0.26
    æĪĺ
    0.26
    amate
    0.25
     Barr
    0.23
    _qual
    0.23
    ç¦Ģ
    0.23
    Activations Density 2.924%

    No Known Activations