© 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. 39643
    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
     product
    -0.28
    OLON
    -0.28
     exploration
    -0.26
     X
    -0.25
     me
    -0.25
     present
    -0.25
     Maya
    -0.25
     modern
    -0.25
     minor
    -0.24
     test
    -0.24
    POSITIVE LOGITS
    ä¸įåĩº
    0.28
    %c
    0.28
    :animated
    0.28
    atten
    0.28
    affles
    0.27
    limits
    0.26
    anked
    0.26
    æķĪçİĩ
    0.25
    orio
    0.25
    ersistent
    0.25
    Activations Density 7.321%

    No Known Activations

    This feature has no known activations.