© 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. 89674
    Prev
    Next
    INDEX
    Explanations

    Possessive or contraction "'s"

    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
    åľ¨ç½ij绾
    -0.25
     uu
    -0.24
    jin
    -0.24
    派驻
    -0.24
    hash
    -0.23
    them
    -0.23
    kommen
    -0.23
    èĩ´åij½
    -0.23
    说ä¸įåĩº
    -0.23
    past
    -0.23
    POSITIVE LOGITS
    å³Ļ
    0.27
    åİŁåĪĻ
    0.25
    饫
    0.25
    req
    0.25
    ä½įç½®
    0.24
     attorney
    0.24
    ªĮ
    0.24
    dtype
    0.24
     borderTop
    0.23
    ponge
    0.23
    Activations Density 27.254%

    No Known Activations