© 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. 30-TRANSCODER-HP
    7. 96873
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æķķ
    -0.27
    æĿµ
    -0.27
    Inst
    -0.26
    åĬĽåѦ
    -0.26
    stell
    -0.26
    模ç³Ĭ
    -0.26
    inst
    -0.26
    å®ļå¾ĭ
    -0.26
    -place
    -0.25
    让åѦçĶŁ
    -0.25
    POSITIVE LOGITS
     zeroes
    0.27
    mers
    0.27
    ä¸ŃåĽ½
    0.26
    rpc
    0.25
    defs
    0.24
     Topics
    0.24
    å»ĵ
    0.24
     Topic
    0.24
     wants
    0.24
    _EXIT
    0.24
    Activations Density 0.107%

    No Known Activations