© 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. 14-TRANSCODER-HP
    7. 39645
    Prev
    Next
    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .decorate
    -0.30
    æĻ¨æĬ¥
    -0.28
    preneur
    -0.27
    esan
    -0.27
    isan
    -0.26
    iguous
    -0.25
    der
    -0.25
    èĭ¦æģ¼
    -0.25
     mojo
    -0.25
    AGED
    -0.24
    POSITIVE LOGITS
    æĬĢæľ¯æĶ¯æĮģ
    0.28
    DEF
    0.27
     wit
    0.25
    æľĽ
    0.25
     fir
    0.24
    çŀĦåĩĨ
    0.24
    wit
    0.24
     vinc
    0.24
    hir
    0.24
    çĩ§
    0.24
    Activations Density 1.947%

    No Known Activations