© 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. 99050
    Prev
    Next
    INDEX
    Explanations

    Technical content

    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
    éĩijåŃĹ
    -0.28
    .forName
    -0.25
    åĩłåĪĨ
    -0.25
    éĽĨåĽ¢èĤ¡ä»½
    -0.24
     diplomacy
    -0.24
    неÑĨ
    -0.23
    ibli
    -0.23
    ields
    -0.23
     apologise
    -0.23
     CDDL
    -0.23
    POSITIVE LOGITS
    äºĴ
    0.27
    olo
    0.27
    ovo
    0.27
    aram
    0.26
    wi
    0.25
    详ç»ĨçļĦ
    0.25
    iew
    0.25
    paration
    0.24
    emd
    0.24
    缸åħ³äººåijĺ
    0.24
    Activations Density 0.002%

    No Known Activations