© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40762
    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
    Negative Logits
    @",
    -0.27
    娱ä¹IJåľº
    -0.26
     nâ
    -0.25
    éĥ½è®¤ä¸º
    -0.24
    IMATE
    -0.24
    ä½ľèĢħæīĢæľī
    -0.24
     Ibrahim
    -0.24
     observable
    -0.24
    âĤ¬âĦ¢
    -0.24
    |$
    -0.24
    POSITIVE LOGITS
    tower
    0.29
    torch
    0.26
    profil
    0.25
    éģŃéģĩ
    0.25
    letters
    0.25
    人çī©
    0.25
    åIJ«
    0.25
    np
    0.24
    è¯ģ
    0.24
     Silence
    0.24
    Activations Density 15.726%

    No Known Activations

    This feature has no known activations.