© 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. 131028
    Prev
    Next
    INDEX
    Explanations

    lot

    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
    udas
    -0.32
    nants
    -0.26
     Ud
    -0.26
     Åŀu
    -0.26
    ector
    -0.25
    åĢĴ
    -0.25
    educt
    -0.25
    thren
    -0.25
     Blasio
    -0.24
    æĹ¥èĩ³
    -0.24
    POSITIVE LOGITS
     of
    0.26
     nutrit
    0.26
    lu
    0.26
     paper
    0.26
    alis
    0.25
    äºĮåįģå¹´
    0.25
    äºĨèĩªå·±çļĦ
    0.24
    ale
    0.24
    Paper
    0.24
    DE
    0.24
    Activations Density 0.022%

    No Known Activations