© 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. 38728
    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
    çİ°
    -0.31
     Present
    -0.29
    Leon
    -0.28
    ä¸İæѤ
    -0.27
     Variation
    -0.26
    ÙĨا
    -0.26
    åĶ±çīĩ
    -0.26
     Projection
    -0.26
     Interaction
    -0.25
     Extr
    -0.25
    POSITIVE LOGITS
     ÐĶм
    0.32
    ç©ľ
    0.29
    eba
    0.28
    ä¿į
    0.28
    ely
    0.27
     water
    0.27
    å¢IJ
    0.27
    water
    0.27
    çĶ¨æĪ·æıIJä¾Ľ
    0.26
    eci
    0.26
    Activations Density 5.881%

    No Known Activations

    This feature has no known activations.