© 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. 22768
    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
    éĻ¤
    -0.31
    åĩĢ
    -0.30
    æ·¨
    -0.27
    agrams
    -0.26
    imonials
    -0.25
     RW
    -0.24
    彤
    -0.24
    æĿĥ
    -0.24
     RD
    -0.24
    .PageSize
    -0.24
    POSITIVE LOGITS
    acr
    0.29
    cer
    0.27
     accent
    0.25
    åĵĪå°Ķ
    0.24
    dig
    0.24
     cuá»Ļc
    0.24
    LEncoder
    0.24
    acl
    0.24
     cer
    0.24
    dyn
    0.24
    Activations Density 0.000%

    No Known Activations