© 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. 89277
    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
    ounc
    -0.27
     brew
    -0.25
    ÙĦÙħ
    -0.25
    aleb
    -0.25
     rospy
    -0.25
    lsi
    -0.25
    ç»ĸ
    -0.24
    绣çŃ¹æİ¨è¿Ľ
    -0.24
    lte
    -0.23
    lings
    -0.23
    POSITIVE LOGITS
    åĪº
    0.25
    ä¸ĢæĹı
    0.24
    éĤ£ä¸ªäºº
    0.24
    ä¸Ģæŀ¶
    0.23
    ä¸Ģå¹ħ
    0.23
    éĤ£æ®µ
    0.23
    inal
    0.23
    ä¸Ģè¶Ł
    0.23
    ç«ĸ
    0.23
    apsed
    0.23
    Activations Density 2.846%

    No Known Activations

    This feature has no known activations.