© 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. 40796
    Prev
    Next
    INDEX
    Explanations

    code or file paths

    np_max-act-logits · gemini-2.0-flash
    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
    åIJĦ级
    -0.27
     nors
    -0.27
     Bord
    -0.26
    èį·
    -0.24
     recogn
    -0.24
    ledge
    -0.23
    orraine
    -0.23
    æļ§æĺ§
    -0.23
    nard
    -0.23
     Gee
    -0.23
    POSITIVE LOGITS
    DOT
    0.30
     lif
    0.27
     six
    0.27
    rey
    0.27
    çĽį
    0.26
    ç²¾
    0.25
     DOT
    0.24
    ot
    0.24
    Dot
    0.24
    缴èIJ¥
    0.24
    Activations Density 0.867%

    No Known Activations