© 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. 99179
    Prev
    Next
    INDEX
    Explanations

    shape

    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
    soever
    -0.32
     BitmapFactory
    -0.25
    æŃ£å¸¸ä½¿çĶ¨
    -0.24
    shima
    -0.23
    romatic
    -0.22
     Solid
    -0.22
    åľ°ä¸Ĭ
    -0.22
    å©¿
    -0.22
    ulares
    -0.22
    sys
    -0.21
    POSITIVE LOGITS
    less
    0.30
    kick
    0.25
    rances
    0.25
    cle
    0.24
    ocking
    0.24
    ",-
    0.24
     rep
    0.24
     twisted
    0.23
    edin
    0.22
    casting
    0.22
    Activations Density 0.613%

    No Known Activations