© 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. 40097
    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
    “
    -0.28
    _finalize
    -0.27
    æģ¯
    -0.27
    ))+
    -0.26
    åIJ¯
    -0.25
    opl
    -0.24
    HU
    -0.24
     “
    -0.23
     render
    -0.23
    DA
    -0.23
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭå°ij
    0.24
     Rewards
    0.24
    Lists
    0.23
    coach
    0.23
    allocator
    0.23
    lists
    0.23
     Govern
    0.23
    Rose
    0.22
    ä¸Ĭåįĩ
    0.22
     #__
    0.22
    Activations Density 5.294%

    No Known Activations

    This feature has no known activations.