© 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. 23-TRANSCODER-HP
    7. 23621
    Prev
    Next
    INDEX
    Explanations

    intelligence, NSA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħ¥åľº
    -0.28
    常è§ģ
    -0.28
    æŃ£ç¡®
    -0.27
    åıĪ好
    -0.26
    åħ¸åŀĭ
    -0.26
    æĸ°çļĦä¸Ģ
    -0.25
    缺失
    -0.25
     correctly
    -0.25
    æŃ£ç¡®çļĦ
    -0.25
    æľ¬ç½ij
    -0.24
    POSITIVE LOGITS
    ecret
    0.28
    wards
    0.27
    vertisement
    0.27
    bcrypt
    0.27
     espionage
    0.26
    arez
    0.26
    spy
    0.26
    imately
    0.26
    llum
    0.25
     spy
    0.25
    Activations Density 0.015%

    No Known Activations