© 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. 87934
    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
    æīĢåľ¨
    -0.25
     Frankie
    -0.25
    ioned
    -0.24
    缩
    -0.24
    doch
    -0.24
    IFF
    -0.24
    åľ°ä½į
    -0.24
    æµģåĬ¨æĢ§
    -0.24
    æīĢåľ¨çļĦ
    -0.23
    üler
    -0.23
    POSITIVE LOGITS
    oss
    0.29
    ist
    0.27
    å¤ĩ
    0.26
    istr
    0.26
    exp
    0.26
     krist
    0.26
     min
    0.25
    ists
    0.25
    ossa
    0.24
     pains
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.