© 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. 88571
    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
    å¯ĨåĪĩ
    -0.27
    ä½ı
    -0.26
    åģ¥åº·çļĦ
    -0.26
    éĥİ
    -0.25
    ве
    -0.25
    缮åīįå·²ç»ı
    -0.24
    åİĨæŶ
    -0.24
     ÑģÑĤеп
    -0.24
    Live
    -0.23
    é®
    -0.23
    POSITIVE LOGITS
     atop
    0.28
    ers
    0.26
    iggins
    0.25
    åŀĽ
    0.24
    éĸĵ
    0.24
    .Direct
    0.24
    icorn
    0.23
    conditional
    0.23
    éĹ´æİ¥
    0.23
     Dort
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.