© 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. 8629
    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
     *=
    -0.27
    ogh
    -0.27
    charg
    -0.26
    æ³¼
    -0.25
     specifier
    -0.25
     tolerated
    -0.25
    دÙĨ
    -0.25
    åħħ
    -0.25
    åIJ¬å¾Ĺ
    -0.24
    isky
    -0.24
    POSITIVE LOGITS
    ãģıãĤĮ
    0.26
    ellar
    0.26
    å±ŀ
    0.26
    屬
    0.25
    ikki
    0.24
    èĢģ人
    0.24
    manent
    0.24
    à¸ķาราà¸ĩ
    0.23
    =bool
    0.23
    ,True
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.