© 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. 57073
    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
     Commissioners
    -0.25
    çļĦ人æĿ¥è¯´
    -0.24
    finder
    -0.24
    ancell
    -0.24
    uffs
    -0.23
    asher
    -0.23
    hots
    -0.23
     MOM
    -0.23
    doors
    -0.23
     triple
    -0.23
    POSITIVE LOGITS
    æѤæĸĩ
    0.29
     Aqu
    0.27
    æķı
    0.27
    acin
    0.26
    æ·®
    0.26
    ahoma
    0.26
    ndx
    0.25
    级以ä¸Ĭ
    0.24
    (SIG
    0.24
    eme
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.