© 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. 23-TRANSCODER-HP
    7. 24567
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人ãģ¨
    -0.26
    GLOSS
    -0.24
    .acquire
    -0.24
    "strconv
    -0.23
    è¿Ľåľº
    -0.23
    ẻ
    -0.23
    .esp
    -0.22
    oplan
    -0.22
    ona
    -0.22
    [assembly
    -0.22
    POSITIVE LOGITS
    é»ijæ´ŀ
    0.27
    rient
    0.26
    åĩĿ
    0.24
    ighborhood
    0.23
    个æľĪ
    0.23
    &action
    0.23
    heimer
    0.23
    ;}↵↵
    0.23
    raud
    0.23
    itti
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.