© 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. 54781
    Prev
    Next
    INDEX
    Explanations

    a

    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
    æľĢ
    -0.31
     Most
    -0.31
    æľĢåIJĪéĢĤ
    -0.29
    Most
    -0.28
     most
    -0.28
    (flag
    -0.27
    æĹĹ
    -0.26
     buc
    -0.25
    most
    -0.25
    MOST
    -0.25
    POSITIVE LOGITS
    agement
    0.28
    enia
    0.26
     bat
    0.25
     anchor
    0.25
     Cli
    0.25
    ightly
    0.24
     evening
    0.23
    æŃĮåĶ±
    0.23
    enser
    0.23
    oir
    0.23
    Activations Density 0.003%

    No Known Activations