© 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. 89204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ĥģ
    -0.27
    æ¸ļ
    -0.24
     Relatives
    -0.23
    åĽŀçŃĶ
    -0.23
    anted
    -0.23
    achable
    -0.23
    ä»ĺãģij
    -0.23
    æݢ索
    -0.23
    ixin
    -0.22
    FOX
    -0.22
    POSITIVE LOGITS
     vé
    0.31
    urn
    0.27
    份
    0.26
    ä¸į代表
    0.26
    æĬ½
    0.26
    ä¸ĭåİ»
    0.25
    ovich
    0.24
    .loads
    0.24
    ôt
    0.24
    并ä¸įå¤ļ
    0.24
    Activations Density 0.154%

    No Known Activations

    This feature has no known activations.