© 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. 88519
    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
    ä¸į说
    -0.28
    çļİ
    -0.28
    èľ¡
    -0.25
    egin
    -0.25
    åĩłåı¥
    -0.24
    Manual
    -0.23
    çļĦæĪIJåĬŁ
    -0.23
     successes
    -0.23
     UNESCO
    -0.23
    velopment
    -0.23
    POSITIVE LOGITS
    deaux
    0.26
    ió
    0.25
    iasm
    0.24
    è¶ħé¢Ŀ
    0.24
    ãĥ¯ãĤ¤
    0.23
    é¦Ļåij³
    0.23
    大æī¹
    0.23
     prz
    0.23
     vượt
    0.22
     unavoid
    0.22
    Activations Density 0.629%

    No Known Activations

    This feature has no known activations.