© 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. 9-TRANSCODER-HP
    7. 29362
    Prev
    Next
    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ãģ¾ãģĦ
    -0.28
    spb
    -0.26
    DRV
    -0.26
    æĺ¨å¤©
    -0.26
    amel
    -0.25
    YZ
    -0.24
    zw
    -0.24
    Yesterday
    -0.24
     "'.$
    -0.23
     اÙĦتÙĨÙģÙĬØ°ÙĬ
    -0.23
    POSITIVE LOGITS
    ift
    0.27
     bas
    0.27
    FFE
    0.26
    妥
    0.25
    itsu
    0.25
    adoras
    0.24
    oque
    0.24
    æŁ¥æĺİ
    0.23
    $__
    0.23
    adora
    0.23
    Activations Density 3.937%

    No Known Activations