© 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. 33-TRANSCODER-HP
    7. 54583
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĭÑĪ
    -0.28
     ver
    -0.28
    orman
    -0.28
     اÙĦØ¥Ùħ
    -0.28
     cast
    -0.28
    otes
    -0.27
    orate
    -0.26
    Ont
    -0.26
    orno
    -0.25
    casting
    -0.25
    POSITIVE LOGITS
    mons
    0.29
    ç¼°
    0.28
    isel
    0.27
    æĮ¥
    0.27
    unity
    0.26
    /native
    0.26
    ç³
    0.26
    _native
    0.26
    native
    0.26
    meric
    0.26
    Activations Density 0.004%

    No Known Activations