© 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. 8341
    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
    æ°²
    -0.27
     foremost
    -0.26
    çŁ¥éģĵ
    -0.25
    [âĢ¦
    -0.25
    æ²Ł
    -0.25
    ega
    -0.24
    ä¹Ī
    -0.24
    enso
    -0.24
     âĢ¦
    -0.24
    åĨµ
    -0.24
    POSITIVE LOGITS
    åľ¨é¦Ļ港
    0.26
     punitive
    0.25
     kü
    0.25
    åŁ¹
    0.25
    achs
    0.24
    otts
    0.24
     home
    0.24
    ETS
    0.23
    åıĺ
    0.23
     moderated
    0.23
    Activations Density 0.100%

    No Known Activations

    This feature has no known activations.