© 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. 27-TRANSCODER-HP
    7. 8262
    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
    Not in Any Lists

    No Comments

    Negative Logits
    åŃ©åŃIJ
    -0.25
     bä
    -0.25
    æĦīå¿«
    -0.24
    åĨ²çªģ
    -0.24
    [loc
    -0.24
    è¾¹
    -0.24
     hb
    -0.23
    éű
    -0.23
    è§Ħ模æľĢ大
    -0.23
    溲
    -0.23
    POSITIVE LOGITS
    omics
    0.23
    [âĢ¦]
    0.23
    vos
    0.22
     Dzi
    0.22
    G
    0.22
    Gs
    0.22
    åĬŀçIJĨ
    0.22
    endo
    0.22
    .Anchor
    0.22
    çĶ¨èĩªå·±çļĦ
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.