© 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. 27-TRANSCODER-HP
    7. 56386
    Prev
    Next
    INDEX
    Explanations

    ish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     èĭ¥è¦ģ
    -0.27
    åĵįèµ·
    -0.26
    ,Integer
    -0.25
     tÃł
    -0.25
     дела
    -0.25
    idente
    -0.25
     integers
    -0.24
    çľĭåIJij
    -0.24
    /welcome
    -0.24
    ICIAL
    -0.24
    POSITIVE LOGITS
     combined
    0.29
    ÃŃch
    0.28
    infeld
    0.27
    åħįéĻ¤
    0.27
    ä¸Ģ次
    0.26
    /MIT
    0.26
    irt
    0.25
    aco
    0.25
    affe
    0.25
    IRT
    0.25
    Activations Density 0.002%

    No Known Activations