© 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. 56359
    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
     PSU
    -0.32
    pus
    -0.30
    溷
    -0.28
    JP
    -0.26
    esso
    -0.26
    æľĶ
    -0.26
    stin
    -0.25
    anya
    -0.25
     mixture
    -0.24
    essa
    -0.24
    POSITIVE LOGITS
    åİŁå§ĭ
    0.29
    è°ģçŁ¥éģĵ
    0.27
    å¼Ĥè®®
    0.27
    OnError
    0.26
    æŃ£
    0.25
     feudal
    0.25
    primitive
    0.25
     bell
    0.25
    éĴ»çŁ³
    0.24
    om
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.