© 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. 27-TRANSCODER-HP
    7. 7687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DEX
    -0.27
    èµĽ
    -0.27
    #{@
    -0.26
    wash
    -0.26
    cratch
    -0.24
    ãĤĭãĤĪãģĨãģ«
    -0.24
     anticip
    -0.24
    èĩĥ
    -0.24
    Arc
    -0.24
    elho
    -0.23
    POSITIVE LOGITS
     taste
    0.29
    éĩijåŃĹå¡Ķ
    0.28
    åħļç»Ħç»ĩ
    0.26
     pesso
    0.26
     tastes
    0.25
    çļĦ身ä½ĵ
    0.24
    æĮĩ
    0.24
    té
    0.24
    å®ŀéĻħæĥħåĨµ
    0.24
    ãģ¨ãģªãĤĬ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.