© 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. 22-TRANSCODER-HP
    7. 97232
    Prev
    Next
    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    d
    -0.26
     Colo
    -0.25
    Issue
    -0.24
     Tor
    -0.24
    ách
    -0.24
    -issue
    -0.24
    alo
    -0.23
    eward
    -0.23
    Correction
    -0.23
    atonin
    -0.23
    POSITIVE LOGITS
     fullest
    0.37
     immensely
    0.30
    详ç»Ĩ
    0.29
    详ç»ĨçļĦ
    0.28
    rif
    0.28
     optimum
    0.28
     enormously
    0.27
    -Za
    0.27
    ->__
    0.26
    PLEASE
    0.26
    Activations Density 0.012%

    No Known Activations