© 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. 40613
    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
    ega
    -0.30
    itzer
    -0.26
    bü
    -0.25
    kus
    -0.25
    kish
    -0.24
    ktor
    -0.24
     Lakes
    -0.23
    æIJŀ
    -0.23
    ÑĤоÑĢ
    -0.23
    ŀæĢ§
    -0.23
    POSITIVE LOGITS
     swear
    0.26
     borne
    0.26
    çĽĺ
    0.26
    paginate
    0.25
    æĶ¶æķĽ
    0.24
    odom
    0.24
    åıªæĢķ
    0.24
    ç¿ĺ
    0.23
    欢è¿İæĤ¨
    0.23
    åĽ½ç«ĭ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.