© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    opensource
    -0.26
    楼å®ĩ
    -0.25
    ilter
    -0.25
    线索
    -0.24
    isory
    -0.24
    éģĤ
    -0.24
    æ¸ĶèĪ¹
    -0.24
    ارÙĬØ®
    -0.23
    ält
    -0.23
    Ñıз
    -0.23
    POSITIVE LOGITS
     multic
    0.27
     multi
    0.26
     mult
    0.26
     Ned
    0.25
     multin
    0.25
     respect
    0.25
     meter
    0.25
     contamin
    0.25
     met
    0.24
     respects
    0.24
    Activations Density 41.870%

    No Known Activations