© 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. 54795
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     fifty
    -0.53
     seventeen
    -0.52
    äºĶåįģ
    -0.51
     seventy
    -0.51
    ä¸ĥåįģ
    -0.50
    åħ«åįģ
    -0.49
     eighty
    -0.49
     sixty
    -0.49
    åħŃåįģ
    -0.49
     fifteen
    -0.48
    POSITIVE LOGITS
    0.41
    ï¼ĵ
    0.40
    3
    0.38
    4
    0.35
    第
    0.34
    ï¼Ĵ
    0.33
    ä¿©
    0.32
    2
    0.31
    ï¼Ķ
    0.31
    6
    0.30
    Activations Density 0.249%

    No Known Activations