© 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. 39027
    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
    Hel
    -0.28
    ...
    -0.28
    :
    -0.28
    7
    -0.28
    形容
    -0.28
    8
    -0.27
    åĩ¸
    -0.27
    Hi
    -0.27
     Mort
    -0.27
    1
    -0.26
    POSITIVE LOGITS
    lush
    0.29
    ạn
    0.29
    _();↵
    0.29
     instantiated
    0.27
    èĮij
    0.27
    .commit
    0.27
    Å¡t
    0.26
    åIJĦåĮº
    0.25
    ecessary
    0.25
    á»įn
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.