© 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. 52568
    Prev
    Next
    INDEX
    Explanations

    central nervous system

    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
    èĦij
    -0.45
    大èĦij
    -0.43
     Brain
    -0.39
     brain
    -0.38
    èħ¦
    -0.38
    Brain
    -0.35
     brains
    -0.34
     cerebral
    -0.34
    brain
    -0.33
    å¿ĥæĻº
    -0.30
    POSITIVE LOGITS
     N
    0.60
    N
    0.56
    _n
    0.50
    _N
    0.48
    ï¼®
    0.43
     н
    0.43
    .N
    0.43
    -n
    0.42
     peripheral
    0.41
    	N
    0.40
    Activations Density 0.312%

    No Known Activations