© 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. 18-TRANSCODER-HP
    7. 90210
    Prev
    Next
    INDEX
    Explanations

    Waste/Disposal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    esk
    -0.27
    ursed
    -0.26
    .solution
    -0.26
    解åĨ³æĸ¹æ¡Ī
    -0.25
    éĥ½ä¸įèĥ½
    -0.25
    dispose
    -0.25
    posium
    -0.25
    鸥
    -0.25
    éĿ¢ç²ī
    -0.25
    weed
    -0.25
    POSITIVE LOGITS
    erras
    0.27
     Protector
    0.27
    Ñįм
    0.26
    fram
    0.25
    ccione
    0.24
     {}.
    0.24
     nämlich
    0.24
    çĶµåı°
    0.24
    æİĮ
    0.24
    icone
    0.24
    Activations Density 9.016%

    No Known Activations