© 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. 22881
    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
    缴æİ¥
    -0.29
     Direct
    -0.29
     Monthly
    -0.29
     nib
    -0.27
    rib
    -0.27
     direct
    -0.26
     independence
    -0.26
    Occup
    -0.26
    æŀľ
    -0.25
     crunch
    -0.25
    POSITIVE LOGITS
     cheated
    0.29
     boyc
    0.27
    äºĨ大éĩıçļĦ
    0.27
    çļĦåŃĺåľ¨
    0.26
     acted
    0.25
    ä¸ĸçķĮçļĦ
    0.25
    åĢ¦
    0.25
    ä½łåºĶ该
    0.24
    /apis
    0.24
    å¤ļä¸ªåĽ½å®¶
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.