© 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. 12-TRANSCODER-HP
    7. 23830
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     credit
    -0.31
    OA
    -0.30
    kw
    -0.30
    ota
    -0.29
    endon
    -0.29
     kw
    -0.28
     chop
    -0.28
    enza
    -0.27
    ãĥ¥
    -0.26
    åIJŀ
    -0.26
    POSITIVE LOGITS
    adle
    0.29
    å²ģæŶ
    0.28
     War
    0.28
    ä»ĬçĶŁ
    0.27
    irling
    0.26
    å¸Ĥåľºç«ŀäºī
    0.26
    iefs
    0.25
    ÙĬسر
    0.24
     raced
    0.24
    IEL
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.