© 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. 32-TRANSCODER-HP
    7. 43890
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīå¿ħè¦ģ
    -0.25
    lov
    -0.24
     Sweep
    -0.24
    åĮĸåIJĪ
    -0.24
     sweep
    -0.24
    -Smith
    -0.23
    æĦļ
    -0.23
    ıntı
    -0.23
     Ames
    -0.23
    æļĤ
    -0.23
    POSITIVE LOGITS
    åĺī
    0.28
    VO
    0.28
    cka
    0.27
    des
    0.26
     об
    0.26
    datum
    0.26
    ouro
    0.26
    dist
    0.26
    (Bit
    0.26
     за
    0.25
    Activations Density 0.009%

    No Known Activations