© 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. 40015
    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
    agli
    -0.28
    åį·
    -0.27
    ernal
    -0.27
    çľ·
    -0.25
     Highest
    -0.24
    Multiplicity
    -0.24
    hest
    -0.23
     ör
    -0.23
    ertools
    -0.23
     Compression
    -0.23
    POSITIVE LOGITS
     stil
    0.28
    .ON
    0.24
    THE
    0.23
    finance
    0.23
    antee
    0.23
    	swap
    0.23
    CISION
    0.22
    _ratings
    0.21
    å°ıéķĩ
    0.21
    ViewInit
    0.21
    Activations Density 61.710%

    No Known Activations

    This feature has no known activations.