© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86972
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    placed
    -0.29
    uce
    -0.29
    eness
    -0.28
    uced
    -0.27
    å¥ĸéĩij
    -0.25
    CardContent
    -0.24
    ÑĪÑĥ
    -0.24
    ician
    -0.24
    æ³·
    -0.23
    coordinate
    -0.23
    POSITIVE LOGITS
    åĨħãģ®
    0.34
    åĨħçļĦ
    0.32
    ä¸ģ
    0.30
    çĶŁæ´»
    0.30
    æĢ»ä½ĵè§ĦåĪĴ
    0.29
    ä¸īæľŁ
    0.29
    åĨħ
    0.28
    ä¸ĢæľŁ
    0.26
     towers
    0.25
     Insider
    0.25
    Activations Density 0.064%

    No Known Activations