© 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. 88501
    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
    zers
    -0.27
    aska
    -0.27
    该åİ¿
    -0.27
    ç¿Ĵ
    -0.26
    æĹ¥åŃIJ
    -0.25
    chestra
    -0.25
    _CONTROLLER
    -0.25
    opia
    -0.24
    posable
    -0.24
    åij¨æģ©
    -0.24
    POSITIVE LOGITS
    åįķ项
    0.27
    åIJĮæĹ¶ä¹Łæĺ¯
    0.25
    .Positive
    0.24
     torn
    0.24
    MS
    0.24
    缯
    0.24
     Living
    0.23
    ç½ij讯
    0.23
     SIN
    0.23
     veloc
    0.23
    Activations Density 0.228%

    No Known Activations

    This feature has no known activations.