© 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. 52579
    Prev
    Next
    INDEX
    Explanations

    genealogy and resources

    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
    acula
    -0.29
     slapped
    -0.25
     Tec
    -0.24
    æīĢ产çĶŁçļĦ
    -0.24
     ${(
    -0.24
    bw
    -0.23
    ocale
    -0.23
     flipped
    -0.23
    è´¬åĢ¼
    -0.23
     Sense
    -0.23
    POSITIVE LOGITS
     resource
    0.29
     Resource
    0.29
    ä¸įçķĻ
    0.28
    .resource
    0.27
     gate
    0.27
    	Resource
    0.26
    Resource
    0.26
     Report
    0.26
    CD
    0.26
    å³Ĵ
    0.25
    Activations Density 0.007%

    No Known Activations