© 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. 39280
    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
    令
    -0.30
     revolves
    -0.30
    è¯ķ
    -0.28
    å°Ĩ以
    -0.28
    æİĸ
    -0.27
    串
    -0.26
    éĵ¶
    -0.26
     din
    -0.26
    æĹĭ
    -0.25
     Shaft
    -0.25
    POSITIVE LOGITS
    çļĦç«ŀäºī
    0.26
    .getSimpleName
    0.26
    kus
    0.26
    ãģ©ãģĵ
    0.26
    achers
    0.26
    PropertyDescriptor
    0.25
    ellij
    0.24
     Runnable
    0.24
     Neue
    0.24
    EObject
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.