© 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. 27-TRANSCODER-HP
    7. 8072
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    useum
    -0.26
    ç«ŀéĢī
    -0.25
    onaut
    -0.24
    ohl
    -0.24
    ä¸İåıijå±ķ
    -0.23
    èľĺèĽĽ
    -0.23
    çĻ¾ç§ij
    -0.23
    .TO
    -0.23
     wants
    -0.22
    è¡ħ
    -0.22
    POSITIVE LOGITS
    locks
    0.26
    optimize
    0.24
    éļIJ
    0.23
    åĴĮä»ĸçļĦ
    0.23
     deals
    0.23
    ä¸ĭ乡
    0.23
     sorts
    0.23
     Respons
    0.23
     cage
    0.23
    //↵↵↵
    0.22
    Activations Density 0.129%

    No Known Activations

    This feature has no known activations.