© 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. 39095
    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
    æ¡ij
    -0.27
    é¦
    -0.26
    ('@
    -0.25
    eters
    -0.24
    磺
    -0.24
    IJľ
    -0.22
     Sant
    -0.22
    erra
    -0.22
    ä½ľä¸ºä¸ĢåIJį
    -0.22
    efs
    -0.21
    POSITIVE LOGITS
    强迫
    0.27
    antry
    0.26
     cropped
    0.24
    sizei
    0.23
    .UnitTesting
    0.23
    é»ijèī²
    0.23
    è·³è·ĥ
    0.23
    phia
    0.23
     bothers
    0.22
    .pitch
    0.22
    Activations Density 12.482%

    No Known Activations

    This feature has no known activations.