© 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. 111022
    Prev
    Next
    INDEX
    Explanations

    code/web snippets

    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
     lẽ
    -0.25
    çłĶ究æĬ¥åijĬ
    -0.25
    InSection
    -0.24
    ãĥ¬ãĤ¹ãĥĪãĥ©ãĥ³
    -0.24
    åĩºåħ·
    -0.24
     pé
    -0.24
    èģĶ社
    -0.24
    .yaml
    -0.24
    chnitt
    -0.23
     cond
    -0.23
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.29
    ablish
    0.28
    å°ķ
    0.26
    cause
    0.26
    ä¸įæĸŃåĪĽæĸ°
    0.25
    ns
    0.24
    åĴĮæľįåĬ¡
    0.23
    å°±è¿ij
    0.23
    AppComponent
    0.22
    urious
    0.22
    Activations Density 0.016%

    No Known Activations