© 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. 29358
    Prev
    Next
    INDEX
    Explanations

    2

    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
    æıIJåĩºçļĦ
    -0.26
    ategy
    -0.26
     stake
    -0.25
    eki
    -0.25
    hair
    -0.25
    straction
    -0.24
    åij³
    -0.24
     bridge
    -0.24
    utas
    -0.24
    çªŁ
    -0.24
    POSITIVE LOGITS
    è¿Ļæĺ¯æĪij们
    0.26
    å¹³æķ´
    0.26
    æĺ¯æĪij们
    0.25
    éķĬ
    0.24
    act
    0.24
     Planet
    0.24
     Mob
    0.24
    çĸıæķ£
    0.23
    æĮ«æĬĺ
    0.23
     cycl
    0.23
    Activations Density 2.618%

    No Known Activations