© 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. 88762
    Prev
    Next
    INDEX
    Explanations

    ln/log

    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
     Dank
    -0.28
     blames
    -0.27
    Hair
    -0.27
    åĽŀæĥ³
    -0.26
    mall
    -0.26
     thanks
    -0.26
    æĥľ
    -0.26
    æĦŁè°¢
    -0.25
    éĨª
    -0.25
    æīģ
    -0.25
    POSITIVE LOGITS
    tru
    0.29
    inh
    0.26
    人
    0.26
    -pressure
    0.25
     fs
    0.25
    ìłĪ
    0.25
    enu
    0.24
     Sar
    0.24
    åģļ
    0.24
    tere
    0.23
    Activations Density 0.029%

    No Known Activations