© 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. 22-TRANSCODER-HP
    7. 86772
    Prev
    Next
    INDEX
    Explanations

    computer-generated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     comprehension
    -0.28
     relative
    -0.27
     chair
    -0.26
    èµŀåĬ©
    -0.26
     table
    -0.26
     Relative
    -0.26
    ä¼ļ让
    -0.25
    s
    -0.25
    çľĭè§ģ
    -0.24
     Cos
    -0.24
    POSITIVE LOGITS
    èµ·äºĨ
    0.27
    (blog
    0.27
    è¿ŀè½½
    0.25
    产çĶŁäºĨ
    0.25
     Scalars
    0.25
     uncert
    0.25
     pagan
    0.24
    iators
    0.24
    éĴª
    0.24
    udes
    0.24
    Activations Density 0.001%

    No Known Activations