© 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. 52534
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     Commit
    -0.27
    ç¾²
    -0.26
    vik
    -0.26
    pei
    -0.25
    esse
    -0.24
    .createServer
    -0.24
    ãĥĵãĥ¼
    -0.23
    éŀį
    -0.23
    asses
    -0.23
    arm
    -0.23
    POSITIVE LOGITS
    -mar
    0.29
     leveled
    0.27
    ienen
    0.27
    æ°ij
    0.27
     levy
    0.26
    -digit
    0.24
     Marathon
    0.24
    extField
    0.24
    Marsh
    0.24
    ething
    0.24
    Activations Density 0.011%

    No Known Activations