© 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. 88173
    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
    éĻIJ度
    -0.27
     studios
    -0.25
    ibox
    -0.24
    nh
    -0.23
    Mir
    -0.23
    cdb
    -0.23
    åĿij
    -0.23
    æĨĭ
    -0.22
    åıĭè°Ĭ
    -0.22
     are
    -0.22
    POSITIVE LOGITS
    ä¸ŃåŃĺåľ¨çļĦ
    0.25
    ↵                    ↵
    0.25
    å¹»æĥ³
    0.24
     bitten
    0.23
     —↵↵
    0.23
    awning
    0.23
    uffs
    0.23
    >Status
    0.23
    ional
    0.23
     invo
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.