© 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. 57961
    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
    å·´åŁº
    -0.28
    ='../
    -0.24
     cig
    -0.24
    (Uri
    -0.24
     glide
    -0.24
    uml
    -0.23
     Ult
    -0.23
    åĽĽäºĶ
    -0.23
    _Begin
    -0.23
    æķ´è½¦
    -0.23
    POSITIVE LOGITS
    人éĹ´
    0.30
     theater
    0.27
    åı£ä¸Ń
    0.26
    cycles
    0.26
    -sharing
    0.26
     mouths
    0.25
     Springs
    0.25
     Codes
    0.24
    imony
    0.24
     obsolete
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.