© 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. 8138
    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
    par
    -0.26
    æĸ°ä¸ŃåĽ½
    -0.25
     fasc
    -0.25
    elines
    -0.25
     cassette
    -0.25
     unauthorized
    -0.24
    åIJ¸
    -0.24
     escalated
    -0.24
     brit
    -0.24
    è®®
    -0.24
    POSITIVE LOGITS
    anzi
    0.31
    GROUND
    0.28
    achi
    0.26
    á¹ĥ
    0.26
    grounds
    0.26
    以ä¸Ĭ
    0.25
    reff
    0.25
    INU
    0.24
    ground
    0.24
    å©´
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.