© 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. 30-TRANSCODER-HP
    7. 94904
    Prev
    Next
    INDEX
    Explanations

    oil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ber
    -0.27
     pan
    -0.25
     rightful
    -0.25
    uten
    -0.25
    pan
    -0.25
    iments
    -0.24
    ut
    -0.24
    Õ¥
    -0.24
    Toy
    -0.24
     tran
    -0.24
    POSITIVE LOGITS
    æĹ¥çĶµ
    0.32
    ½Ķ
    0.25
    ãģŀ
    0.25
    ;]/
    0.24
    EXPORT
    0.24
    -controls
    0.24
     savedInstanceState
    0.24
    иÑİ
    0.24
    çĶ¨æĿ¥
    0.24
     setContentView
    0.23
    Activations Density 1.001%

    No Known Activations