© 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. 22-TRANSCODER-HP
    7. 98851
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unm
    -0.27
    orrent
    -0.26
    ä¸į容
    -0.25
     Ryu
    -0.25
    REE
    -0.25
    oine
    -0.25
    åĨ³è®®
    -0.25
    å¸Ŀçİĭ
    -0.25
    缴è¾ĸ
    -0.24
     unh
    -0.24
    POSITIVE LOGITS
    _generated
    0.28
    åī¯
    0.25
    ample
    0.25
    å¹»
    0.24
     conver
    0.24
    ä¸Ģ段
    0.24
    温
    0.23
    "urls
    0.23
    zier
    0.23
    -sample
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.