© 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. 35-TRANSCODER-HP
    7. 39917
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.29
     denn
    -0.28
    etus
    -0.28
     Retro
    -0.27
    rys
    -0.26
    iven
    -0.26
     bele
    -0.26
    æĸ¹ä¾¿
    -0.24
    aires
    -0.24
    bre
    -0.24
    POSITIVE LOGITS
     expl
    0.26
     bolt
    0.24
    eut
    0.23
    ichen
    0.23
    ä¾Ŀæ³ķ
    0.23
    cosa
    0.23
    ayo
    0.23
    åį±éĻ©
    0.23
    plit
    0.23
    orf
    0.23
    Activations Density 61.884%

    No Known Activations

    This feature has no known activations.