© 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. 7896
    Prev
    Next
    INDEX
    Explanations

    -

    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
    åĢ«
    -0.27
    ENA
    -0.26
     mortal
    -0.26
    plevel
    -0.26
    æĿĢæŃ»
    -0.25
    Alive
    -0.24
     Mort
    -0.24
     ever
    -0.24
     CLICK
    -0.24
    饿
    -0.23
    POSITIVE LOGITS
    antine
    0.29
    æŀĦçŃij
    0.27
    æµĵåİļ
    0.26
    çŃĶåį·
    0.26
    ><![
    0.26
    æĢ»ä¹¦è®°åľ¨
    0.25
    çĨĬçĮ«
    0.25
    away
    0.24
    -labelledby
    0.24
    orian
    0.24
    Activations Density 0.012%

    No Known Activations