© 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. 56585
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    logan
    -0.28
    å®Ī
    -0.27
    san
    -0.27
     farmer
    -0.27
    act
    -0.26
    ëĮĢ
    -0.26
    åķĨ
    -0.26
    alog
    -0.26
    assin
    -0.25
     Omn
    -0.25
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.33
    åIJ¬è¯´è¿ĩ
    0.32
     unintention
    0.31
     evident
    0.28
     any
    0.27
     swelling
    0.27
     ever
    0.27
    persistent
    0.26
     inadvertently
    0.26
    (Throwable
    0.26
    Activations Density 0.004%

    No Known Activations