© 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. 30468
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     safest
    -0.30
     safe
    -0.27
    .ent
    -0.26
     kre
    -0.26
    utow
    -0.26
    ypress
    -0.25
    storage
    -0.24
    åijĻ
    -0.24
     increase
    -0.24
    åĨĻåŃĹ
    -0.24
    POSITIVE LOGITS
    迹
    0.28
     contacto
    0.27
    æݥ触
    0.27
     pier
    0.26
     Nil
    0.26
     bored
    0.26
    aled
    0.26
    侦
    0.25
    å¥Ĺ
    0.25
    è¾¹
    0.25
    Activations Density 1.406%

    No Known Activations