© 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. 86990
    Prev
    Next
    INDEX
    Explanations

    computer

    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
    )>>
    -0.26
    COND
    -0.25
     maintained
    -0.25
    )obj
    -0.25
     maint
    -0.24
     tol
    -0.24
    ACY
    -0.24
     Passage
    -0.24
    RIPT
    -0.24
    .flat
    -0.24
    POSITIVE LOGITS
    opsis
    0.29
    彦
    0.28
    è¿Ŀæ³ķè¿Ŀè§Ħ
    0.24
    æīĺ管
    0.24
    è°ģçŁ¥
    0.23
    è´ŃæĪ¿
    0.23
    è°ģçŁ¥éģĵ
    0.23
    æĬĺ
    0.23
    -engine
    0.23
    adb
    0.23
    Activations Density 0.001%

    No Known Activations