© 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. 88926
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    æĿŀ
    -0.24
    é²Ľ
    -0.24
    è¾¹å¢ĥ
    -0.24
    IllegalAccessException
    -0.23
     youre
    -0.23
    neo
    -0.23
    orphic
    -0.23
     nowhere
    -0.23
     tÃł
    -0.22
    -neck
    -0.22
    POSITIVE LOGITS
    lator
    0.25
    ivity
    0.25
    TestFixture
    0.24
    ::$_
    0.24
    fed
    0.24
    çł»
    0.24
    laÅŁtır
    0.24
     CFL
    0.23
    ya
    0.23
     Fey
    0.23
    Activations Density 0.151%

    No Known Activations